release v0.4.4

* split __train up for clarity

* split __train up for clarity

* added lr scheduler after epoch completes

.codecov.yml

@@ -0,0 +1,44 @@
+#see https://github.com/codecov/support/wiki/Codecov-Yaml
+codecov:
+  notify:
+    require_ci_to_pass: yes
+
+coverage:
+  precision: 0  # 2 = xx.xx%, 0 = xx%
+  round: nearest # how coverage is rounded: down/up/nearest
+  range: 40...100 # custom range of coverage colors from red -> yellow -> green
+  status:
+    # https://codecov.readme.io/v1.0/docs/commit-status
+    project:
+      default:
+        against: auto
+        target: 99% # specify the target coverage for each commit status
+        threshold: 20% # allow this little decrease on project
+        # https://github.com/codecov/support/wiki/Filtering-Branches
+        # branches: master
+        if_ci_failed: error
+    # https://github.com/codecov/support/wiki/Patch-Status
+    patch:
+      default:
+        against: auto
+        target: 40% # specify the target "X%" coverage to hit
+        # threshold: 50% # allow this much decrease on patch
+    changes: false
+
+parsers:
+  gcov:
+    branch_detection:
+      conditional: true
+      loop: true
+      macro: false
+      method: false
+  javascript:
+    enable_partials: false
+
+comment:
+  layout: header, diff
+  require_changes: false
+  behavior: default  # update if exists else create new
+  # branches: *
+
+

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,36 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+### Common bugs:
+1. Tensorboard not showing in Jupyter-notebook see [issue 79](https://github.com/williamFalcon/pytorch-lightning/issues/79).    
+2. PyTorch 1.1.0 vs 1.2.0 support [see FAQ](https://github.com/williamFalcon/pytorch-lightning#faq)    
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement, help wanted
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/typos-and-doc-fixes.md

@@ -0,0 +1,17 @@
+---
+name: Typos and doc fixes
+about: Typos and doc fixes
+title: ''
+labels: typo
+assignees: ''
+
+---
+
+For typos and doc fixes, please go ahead and:
+
+1. Create an issue.
+2. Fix the typo.   
+3. Submit a PR.
+
+
+Thanks!

.gitignore

@@ -9,6 +9,8 @@ model_weights/
 app/models/
 pip-wheel-metadata/
 test_tube_exp/
+tests/tests_tt_dir/
+tests/save_dir
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -119,4 +121,4 @@ ENV/
 .mypy_cache/
 
 # data
-mnist/
+mnist/

.readthedocs.yml

@@ -0,0 +1,19 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation with MkDocs
+mkdocs:
+  configuration: mkdocs.yml
+
+# Optionally build your docs in additional formats such as PDF and ePub
+formats: all
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.7
+  install:
+    - requirements: docs/requirements.txt

.travis.yml

@@ -0,0 +1,46 @@
+# vim ft=yaml
+
+# After changing this file, check it on:
+#   http://yaml-online-parser.appspot.com/
+
+# See doc/travis_notes.txt for some guidelines
+
+# this file is *not* meant to cover or endorse the use of travis, but rather to
+# help confirm pull requests to this project.
+
+dist: xenial  # Ubuntu 16.04
+
+env:
+  global:
+    - DISPLAY=""
+
+language: python
+
+matrix:
+  include:
+    - python: 3.6
+      env: TOXENV=py36
+    - python: 3.7
+      env: TOXENV=py37
+
+# See http://docs.travis-ci.com/user/caching/#pip-cache
+cache: pip
+
+install:
+  - pip install -r requirements.txt
+  - pip install -r ./tests/requirements.txt
+  - pip --version ; pip list
+
+script:
+  # integration
+  - tox --sitepackages
+  - python setup.py install --dry-run
+
+after_success:
+  - coverage report
+  # disable auto coverage bc it isn't accurate since it misses gpu code.
+  # to get coverage, run local and push results
+  # - codecov
+
+notifications:
+  email: false

CODE_OF_CONDUCT.md

@@ -0,0 +1,76 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+ advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+ address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+ professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at waf2107@columbia.edu. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq

CONTRIBUTING.md

@@ -0,0 +1,37 @@
+# Contributing    
+Welcome to the PyTorch Lightning community! We're building the most advanced research platform on the planet to implement the latest, best practices that the amazing PyTorch team rolls out!  
+
+## Lightning Design Principles   
+We encourage all sorts of contributions you're interested in adding! When coding for lightning, please follow these principles.    
+
+#### No PyTorch interference   
+We don't want to add any abstractions on top of pure PyTorch. This gives researchers all the control they need without having to learn yet another framework.    
+
+#### Simple Internal Code    
+It's useful for users to look at the code and understand very quickly what's happening. Many users won't be engineers. Thus we need to value clear, simple code over condensed ninja moves. While that's super cool, this isn't the project for that :)      
+
+#### Force User Decisions To Best Practices    
+There are 1,000 ways to do something. However, something eventually becomes standard practice that everyone does. Thus we pick one way of doing it and force everyone to do it this way. A good example is accumulated gradients. There are many ways to implement, we just pick one and force users to use that one. A bad forced decision would be to make users use a specific library to do something.    
+
+When something becomes a best practice, we add it to the framework. This likely looks like code in utils or in the model file that everyone keeps adding over and over again across projects. When this happens, bring that code inside the trainer and add a flag for it.
+
+#### Simple External API    
+What makes sense to you may not make sense to others. Create an issue with an API change suggestion and validate that it makes sense for others. Treat code changes how you treat a startup: validate that it's a needed feature, then add if it makes sense for many people.    
+
+#### Gain User Trust    
+As a researcher you can't have any part of your code going wrong. So, make thorough tests that ensure an implementation of a new trick or subbtle change is correct.    
+
+## Contribution types    
+Currently looking for help implementing new features or adding bug fixes. 
+
+A lot of good work has already been done in project mechanics (requirements.txt, setup.py, pep8, badges, ci, etc...) we're in a good state there thanks to all the early contributors (even pre-beta release)!   
+
+## Bug fixes:  
+1. Submit a github issue.   
+2. Fix it.  
+3. Submit a PR! 
+
+## New Features:  
+1. Submit a github issue.   
+2. We'll agree on the feature scope.     
+3. Submit a PR! (with updated docs and tests 🙃).   

COPYING

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2019 William Falcon
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

@@ -1,9 +1,37 @@
-graft docs
+# Manifest syntax https://docs.python.org/2/distutils/sourcedist.html
+graft wheelhouse
 
-include COPYING
-include AUTHORS
+recursive-include birl *.py
+recursive-exclude __pycache__  *.py[cod] *.orig
 
-recursive-include src/einsteinpy/tests *.py *.html
+# Include the README
+include *.md
 
-prune docs/source/examples/.ipynb_checkpoints
-global-exclude *.py[cod] __pycache__ *.so *.dylib
+# Include the license file
+include LICENSE
+
+exclude *.sh
+exclude *.toml
+exclude *.svg    
+recursive-include examples *.py
+recursive-include pytorch_lightning *.py
+
+# exclude tests from package
+recursive-exclude tests *
+exclude tests
+
+# Exclude the documentation files
+recursive-exclude docs *
+exclude docs
+
+# Include the Requirements
+include requirements.txt
+
+# Exclude build configs
+exclude *.yml
+
+prune .git
+prune .github
+prune notebook*
+prune temp*
+prune test*

README.md

@@ -1,43 +1,165 @@
-<p align="center">
-  <a href="https://williamfalcon.github.io/pytorch-lightning/">
-    <img alt="" src="https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/lightning_logo.png" width="50">
-  </a>
-</p>
-<h3 align="center">
-  Pytorch Lightning
-</h3>
-<p align="center">
-  The Keras for ML researchers using PyTorch. More control. Less boilerplate.    
-</p>
-<p align="center">
-  <a href="https://badge.fury.io/py/pytorch-lightning"><img src="https://badge.fury.io/py/pytorch-lightning.svg" alt="PyPI version" height="18"></a>
-<!--   <a href="https://travis-ci.org/williamFalcon/test-tube"><img src="https://travis-ci.org/williamFalcon/pytorch-lightning.svg?branch=master"></a> -->
-  <a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/COPYING"><img src="https://img.shields.io/badge/License-MIT-yellow.svg"></a>
-</p>   
+<div align="center">
 
+![Logo](./docs/source/_static/lightning_logo_small.png)
+
+# PyTorch Lightning
+
+**The PyTorch Keras for ML researchers. More control. Less boilerplate.**
+
+
+[![PyPI Status](https://badge.fury.io/py/pytorch-lightning.svg)](https://badge.fury.io/py/pytorch-lightning)
+[![PyPI Status](https://pepy.tech/badge/pytorch-lightning)](https://pepy.tech/project/pytorch-lightning)
+[![Build Status](https://travis-ci.org/williamFalcon/pytorch-lightning.svg?branch=master)](https://travis-ci.org/williamFalcon/pytorch-lightning)
+<!-- 
+removed until windows install issues resolved.
+[![Build status](https://ci.appveyor.com/api/projects/status/rum89d7hq8l1kfye?svg=true)](https://ci.appveyor.com/project/Borda/pytorch-lightning) -->
+<!-- 
+removed until codecov badge isn't empy. likely a config error showing nothing on master.
+[![codecov](https://codecov.io/gh/Borda/pytorch-lightning/branch/master/graph/badge.svg)](https://codecov.io/gh/Borda/pytorch-lightning)
+-->
+[![Coverage](https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/coverage.svg)](https://github.com/williamFalcon/pytorch-lightning/tree/master/tests#running-coverage)
+[![CodeFactor](https://www.codefactor.io/repository/github/borda/pytorch-lightning/badge)](https://www.codefactor.io/repository/github/borda/pytorch-lightning)
+[![ReadTheDocs](https://readthedocs.org/projects/pytorch-lightning/badge/?version=latest)](https://pytorch-lightning.readthedocs.io/en/latest)
+[![license](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/williamFalcon/pytorch-lightning/blob/master/LICENSE)
+
+</div>
+
+Simple installation from PyPI
 ```bash
-pip install pytorch-lightning    
+pip install pytorch-lightning  
 ```
 
 ## Docs   
 **[View the docs here](https://williamfalcon.github.io/pytorch-lightning/)**
 
 ## What is it?  
-Keras and fast.ai are too abstract for researchers. Lightning abstracts the full training loop but gives you control in the critical points.   
+Lightning is a very lightweight wrapper on PyTorch. This means you don't have to learn a new library. It defers core training and validation logic to you and automates the rest. It guarantees tested, correct, modern best practices for the automated parts.
 
 
 ## Why do I want to use lightning?
-Because you don't want to define a training loop, validation loop, gradient clipping, checkpointing, loading, 
-gpu training, etc... every time you start a project. Let lightning handle all of that for you! Just define your 
-data and what happens in the training, testing and validation loop and lightning will do the rest.
+When starting a new project the last thing you want to do is recode a training loop, multi-cluster training, 16-bit precision, early-stopping, model loading/saving, when to validate, etc... You're likely to spend a long time ironing out all the bugs without even getting to the core of your research.
+
+With lightning, you guarantee those parts of your code work so you can focus on what the meat of the research: The data and the training/validation loop logic. 
+
+Don't worry about training on multiple gpus or speeding up your code, lightning will do that for you!
+
+---   
+## README Table of Contents        
+- [How do I use it](https://github.com/williamFalcon/pytorch-lightning#how-do-i-do-use-it)     
+- [What lightning automates](https://github.com/williamFalcon/pytorch-lightning#what-does-lightning-control-for-me)    
+- [Tensorboard integration](https://github.com/williamFalcon/pytorch-lightning#tensorboard)    
+- [Lightning features](https://github.com/williamFalcon/pytorch-lightning#lightning-automates-all-of-the-following-each-is-also-configurable)    
+- [Demos](https://github.com/williamFalcon/pytorch-lightning#demo)    
+- [Tutorials](https://github.com/williamFalcon/pytorch-lightning#tutorials)
+- [Contributing](https://github.com/williamFalcon/pytorch-lightning/blob/master/CONTRIBUTING.md)    
+- [Bleeding edge install](https://github.com/williamFalcon/pytorch-lightning#bleeding-edge)   
+- [Lightning Design Principles](https://github.com/williamFalcon/pytorch-lightning#lightning-design-principles)
+- [FAQ](https://github.com/williamFalcon/pytorch-lightning#faq)    
+
+---   
+## How do I do use it?   
 
 To use lightning do 2 things:  
-1. [Define a Trainer](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/trainer_cpu_template.py).   
-2. [Define a LightningModel](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/lightning_module_template.py).     
+1. [Define a LightningModel](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/)         
+```python
+import os
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+import torchvision.transforms as transforms
 
-## What does lightning control for me?
-Everything!    
-Except for these 6 core functions which you define:    
+import pytorch_lightning as pl
+
+class CoolModel(pl.LightningModule):
+
+    def __init__(self):
+        super(CoolModel, self).__init__()
+        # not the best model...
+        self.l1 = torch.nn.Linear(28 * 28, 10)
+
+    def forward(self, x):
+        return torch.relu(self.l1(x.view(x.size(0), -1)))
+
+    def training_step(self, batch, batch_nb):
+        # REQUIRED
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'loss': F.cross_entropy(y_hat, y)}
+
+    def validation_step(self, batch, batch_nb):
+        # OPTIONAL
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'val_loss': self.my_loss(y_hat, y)}
+
+    def validation_end(self, outputs):
+        # OPTIONAL
+        avg_loss = torch.stack([x['val_loss'] for x in outputs]).mean()
+        return {'avg_val_loss': avg_loss}
+
+    def configure_optimizers(self):
+        # REQUIRED
+        return [torch.optim.Adam(self.parameters(), lr=0.02)]
+
+    @pl.data_loader
+    def tng_dataloader(self):
+        # REQUIRED
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+
+    @pl.data_loader
+    def val_dataloader(self):
+        # OPTIONAL
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+
+    @pl.data_loader
+    def test_dataloader(self):
+        # OPTIONAL
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+```
+
+2. Fit with a [trainer](https://williamfalcon.github.io/pytorch-lightning/Trainer/)    
+```python
+from pytorch_lightning import Trainer
+
+model = CoolModel()
+
+# most basic trainer, uses good defaults
+trainer = Trainer()    
+trainer.fit(model)   
+```     
+
+Or with tensorboard logger and some options turned on such as multi-gpu, etc...    
+```python   
+from test_tube import Experiment    
+
+# PyTorch summarywriter with a few bells and whistles    
+exp = Experiment(save_dir=os.getcwd())
+
+# train on cpu using only 10% of the data (for demo purposes)
+# pass in experi
+trainer = Trainer(experiment=exp, max_nb_epochs=1, train_percent_check=0.1)
+
+# train on 4 gpus
+# trainer = Trainer(experiment=exp, max_nb_epochs=1, gpus=[0, 1, 2, 3])
+
+# train on 32 gpus across 4 nodes (make sure to submit appropriate SLURM job)
+# trainer = Trainer(experiment=exp, max_nb_epochs=1, gpus=[0, 1, 2, 3, 4, 5, 6, 7], nb_gpu_nodes=4)
+
+# train (1 epoch only here for demo)
+trainer.fit(model)
+
+# view tensorflow logs 
+print('View tensorboard logs by running\ntensorboard --logdir %s' % os.getcwd())
+print('and going to http://localhost:6006 on your browser')
+```    
+
+## What does lightning control for me?   
+
+Everything in gray!    
+You define the blue parts using the LightningModule interface:  
+
+![Ouverview](./docs/source/_static/overview_flat.jpg)
 
 ```{.python}
 # what to do in the training loop
@@ -65,7 +187,7 @@ def training_step(self, data_batch, batch_nb):
     # define your own forward and loss calculation
     hidden_states = self.encoder(x)
      
-    # even as complex as a seq-2seq + attn model
+    # even as complex as a seq-2-seq + attn model
     # (this is just a toy, non-working example to illustrate)
     start_token = '<SOS>'
     last_hidden = torch.zeros(...)
@@ -116,22 +238,14 @@ def validation_end(self, outputs):
     return tqdm_dic
 ```
    
-## TensorboardX    
-Lightning is fully integrated with tensorboardX.   
+## Tensorboard    
+Lightning is fully integrated with tensorboard.   
 
-<p align="center">
-  <a href="https://williamfalcon.github.io/pytorch-lightning/">
-    <img alt="" src="https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/tf_loss.png" width="900px">
-  </a>
-</p>
+![tensorboard-support](./docs/source/_static/tf_loss.png)
 
 Lightning also adds a text column with all the hyperparameters for this experiment.      
 
-<p align="center">
-  <a href="https://williamfalcon.github.io/pytorch-lightning/">
-        <img alt="" src="https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/tf_tags.png" width="900px">
-  </a>
-</p>
+![tensorboard-support](./docs/source/_static/tf_tags.png)
 
 Simply note the path you set for the Experiment    
 ``` {.python}   
@@ -148,12 +262,14 @@ And run tensorboard from that dir
 tensorboard --logdir /some/path     
 ```    
 
-## Lightning automatically automates all of the following ([each is also configurable](https://williamfalcon.github.io/pytorch-lightning/Trainer/)):
+## Lightning automates all of the following ([each is also configurable](https://williamfalcon.github.io/pytorch-lightning/Trainer/)):
+
 
 ###### Checkpointing    
 
 - [Model saving](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#model-saving)
 - [Model loading](https://williamfalcon.github.io/pytorch-lightning/LightningModule/methods/#load-from-metrics) 
+- [Restoring training session](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#restoring-training-session)
 
 ###### Computing cluster (SLURM)    
 
@@ -167,7 +283,8 @@ tensorboard --logdir /some/path
 - [Log GPU usage](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#Log-gpu-usage)
 - [Make model overfit on subset of data](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#make-model-overfit-on-subset-of-data)
 - [Print the parameter count by layer](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-the-parameter-count-by-layer)
-- [Pring which gradients are nan](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-which-gradients-are-nan)
+- [Print which gradients are nan](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-which-gradients-are-nan)
+- [Print input and output size of every module in system](https://williamfalcon.github.io/pytorch-lightning/LightningModule/properties/#example_input_array)
 
 
 ###### Distributed training    
@@ -182,9 +299,9 @@ tensorboard --logdir /some/path
 ###### Experiment Logging   
 
 - [Display metrics in progress bar](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#display-metrics-in-progress-bar)
-- Log arbitrary metrics
 - [Log metric row every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#log-metric-row-every-k-batches)
 - [Process position](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#process-position)
+- [Tensorboard support](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#tensorboard-support)
 - [Save a snapshot of all hyperparameters](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#save-a-snapshot-of-all-hyperparameters) 
 - [Snapshot code for a training run](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#snapshot-code-for-a-training-run) 
 - [Write logs file to csv every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#write-logs-file-to-csv-every-k-batches)
@@ -192,16 +309,18 @@ tensorboard --logdir /some/path
 ###### Training loop    
 
 - [Accumulate gradients](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#accumulated-gradients)
-- [Anneal Learning rate](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#anneal-learning-rate)
 - [Force training for min or max epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-training-for-min-or-max-epochs)
 - [Force disable early stop](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-disable-early-stop)
 - [Gradient Clipping](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#gradient-clipping)
-- [Use multiple optimizers (like GANs)](https://williamfalcon.github.io/pytorch-lightning/Pytorch-Lightning/LightningModule/#configure_optimizers)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
+- [Learning rate scheduling](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)    
+- [Use multiple optimizers (like GANs)](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)
 - [Set how much of the training set to check (1-100%)](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#set-how-much-of-the-training-set-to-check)
 
 ###### Validation loop    
 
 - [Check validation every n epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#check-validation-every-n-epochs)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
 - [Set how much of the validation set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-validation-set-to-check)
 - [Set how much of the test set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-test-set-to-check)
 - [Set validation check frequency within 1 training epoch](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-validation-check-frequency-within-1-training-epoch)
@@ -215,19 +334,52 @@ pip install pytorch-lightning
 
 # clone lightning for the demo
 git clone https://github.com/williamFalcon/pytorch-lightning.git
+cd pytorch-lightning
 cd examples/new_project_templates/
 
-# run demo (on cpu)
-python trainer_gpu_cluster_template.py
+# all of the following demos use the SAME model to show no modification needs to be made to your code
+
+# train on cpu 
+python single_cpu_template.py
+
+# train on multiple-gpus 
+python single_gpu_node_template.py --gpus "0,1"
+
+# train on 32 gpus on a cluster (run on a SLURM managed cluster)
+python multi_node_cluster_template.py --nb_gpu_nodes 4 --gpus '0,1,2,3,4,5,6,7'
 ```
 
-Without changing the model AT ALL, you can run the model on a single gpu, over multiple gpus, or over multiple nodes.
+## Tutorials   
+- [Basic Lightning use](https://towardsdatascience.com/supercharge-your-ai-research-with-pytorch-lightning-337948a99eec)    
+- [9 key speed features in Pytorch-Lightning](https://towardsdatascience.com/9-tips-for-training-lightning-fast-neural-networks-in-pytorch-8e63a502f565)    
+- [SLURM, multi-node training with Lightning](https://towardsdatascience.com/trivial-multi-node-training-with-pytorch-lightning-ff75dfb809bd)     
+
+---   
+## FAQ    
+**Why was Lightning created?**     
+Lightning has 3 goals in mind:
+1. Maximal flexibility while abstracting out the common boilerplate across research projects.   
+2. Reproducibility. If all projects use the LightningModule template, it will be much much easier to understand what's going on and where to look! It will also mean every implementation follows a standard format.   
+3. Democratizing PyTorch power user features. Distributed training? 16-bit? know you need them but don't want to take the time to implement? All good... these come built into Lightning.    
+
+**How does Lightning compare with Ignite and fast.ai?**     
+[Here's a thorough comparison](https://medium.com/@_willfalcon/pytorch-lightning-vs-pytorch-ignite-vs-fast-ai-61dc7480ad8a).    
+
+**Is this another library I have to learn?**    
+Nope! We use pure Pytorch everywhere and don't add unecessary abstractions!   
+
+**Are there plans to support Python 2?**          
+Nope.     
+
+**Are there plans to support virtualenv?**    
+Nope. Please use anaconda or miniconda.    
+
+**Which PyTorch versions do you support?**    
+Lightning 0.4.2+ supports PyTorch 1.2.0.    
+For PyTorch 1.1.0 install Lightning 0.4.0 with test-tube=0.6.7.6.    
+
+## Bleeding edge
+If you can't wait for the next release, install the most up to date code with:  
 ```bash
-# run a grid search on two gpus
-python fully_featured_trainer.py --gpus "0;1"
-
-# run single model on multiple gpus
-python fully_featured_trainer.py --gpus "0;1" --interactive
+pip install git+https://github.com/williamFalcon/pytorch-lightning.git@master --upgrade
 ```
-
-

appveyor.yml

@@ -0,0 +1,66 @@
+# https://www.appveyor.com/docs/appveyor-yml/
+environment:
+
+  # SDK v7.0 MSVC Express 2008's SetEnv.cmd script will fail if the
+  # /E:ON and /V:ON options are not enabled in the batch script interpreter
+  # See: http://stackoverflow.com/a/13751649/163740
+  CMD_IN_ENV: "cmd /E:ON /V:ON /C obvci_appveyor_python_build_env.cmd"
+
+  matrix:
+    # Pre-installed Python versions, which Appveyor may upgrade to
+    # a later point release.
+    # See: http://www.appveyor.com/docs/installed-software#python
+
+
+    # - PYTHON: "C:\\Python35-x64"
+    #   PYTHON_VERSION: "3.5.x"
+    #   PYTHON_ARCH: "64"
+    #  TOXENV: "py35"
+
+    - PYTHON: "C:\\Python36-x64"
+      PYTHON_VERSION: "3.6.x"
+      PYTHON_ARCH: "64"
+      TOXENV: "py36"
+      PIP_PYVER: "36"
+
+    - PYTHON: "C:\\Python37-x64"
+      PYTHON_VERSION: "3.7.x"
+      PYTHON_ARCH: "64"
+      TOXENV: "py37"
+      PIP_PYVER: "37"
+
+build: off
+
+# https://www.appveyor.com/docs/build-cache/
+cache:
+  - C:\ProgramData\chocolatey\bin -> appveyor.yml
+  - C:\ProgramData\chocolatey\lib -> appveyor.yml
+  - '%LOCALAPPDATA%\pip\Cache -> appveyor.yml'
+
+# scripts that run after cloning repository
+install:
+  # If there is a newer build queued for the same PR, cancel this one.
+  # The AppVeyor 'rollout builds' option is supposed to serve the same
+  # purpose but it is problematic because it tends to cancel builds pushed
+  # directly to master instead of just PR builds (or the converse).
+  - SET PATH=%PYTHON%;%PYTHON%\\Scripts;%path%
+  - pip install -U --user pip
+  - pip install "https://download.pytorch.org/whl/cu90/torch-1.1.0-cp%PIP_PYVER%-cp%PIP_PYVER%m-win_amd%PYTHON_ARCH%.whl"
+    pip install "https://download.pytorch.org/whl/cu90/torchvision-0.3.0-cp%PIP_PYVER%-cp%PIP_PYVER%m-win_amd%PYTHON_ARCH%.whl"
+  - pip install -r requirements.txt
+  - pip install -r ./tests/requirements.txt
+
+# scripts to run before tests (working directory and environment changes are persisted from the previous steps such as "before_build")
+before_test:
+  - python --version
+  - pip --version
+  - pip list
+  - dir
+
+# to run your custom scripts instead of automatic tests
+test_script:
+  - tox --sitepackages --parallel auto
+
+on_success:
+  - coverage report
+  # - codecov

docs/LightningModule/RequiredTrainerInterface.md

@@ -3,30 +3,96 @@
 
 A lightning module is a strict superclass of nn.Module, it provides a standard interface for the trainer to interact with the model.
 
-The easiest thing to do is copy [this template](../../examples/new_project_templates/lightning_module_template.py) and modify accordingly. 
+The easiest thing to do is copy the [minimal example](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#minimal-example) below and modify accordingly. 
 
 Otherwise, to Define a Lightning Module, implement the following methods:
 
 **Required**:  
 
 - [training_step](RequiredTrainerInterface.md#training_step)   
-- [validation_step](RequiredTrainerInterface.md#validation_step)
-- [validation_end](RequiredTrainerInterface.md#validation_end)
-    
+- [tng_dataloader](RequiredTrainerInterface.md#tng_dataloader)
 - [configure_optimizers](RequiredTrainerInterface.md#configure_optimizers)
-- [get_save_dict](RequiredTrainerInterface.md#get_save_dict)
-- [load_model_specific](RequiredTrainerInterface.md#load_model_specific)
-
-- [tng_dataloader](RequiredTrainerInterface.md#tng_dataloader)
-- [tng_dataloader](RequiredTrainerInterface.md#tng_dataloader)
-- [test_dataloader](RequiredTrainerInterface.md#test_dataloader)
 
 **Optional**:   
+- [validation_step](RequiredTrainerInterface.md#validation_step)
+- [validation_end](RequiredTrainerInterface.md#validation_end)
+- [val_dataloader](RequiredTrainerInterface.md#val_dataloader)
+- [test_dataloader](RequiredTrainerInterface.md#test_dataloader)
 
+- [on_save_checkpoint](RequiredTrainerInterface.md#on_save_checkpoint)
+- [on_load_checkpoint](RequiredTrainerInterface.md#on_load_checkpoint)
 - [update_tng_log_metrics](RequiredTrainerInterface.md#update_tng_log_metrics)
 - [add_model_specific_args](RequiredTrainerInterface.md#add_model_specific_args)
 
 ---
+### Minimal example   
+```python
+import os
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+import torchvision.transforms as transforms
+
+import pytorch_lightning as pl
+
+class CoolModel(pl.LightningModule):
+
+    def __init__(self):
+        super(CoolModel, self).__init__()
+        # not the best model...
+        self.l1 = torch.nn.Linear(28 * 28, 10)
+
+    def forward(self, x):
+        return torch.relu(self.l1(x.view(x.size(0), -1)))
+
+    def training_step(self, batch, batch_nb):
+        # REQUIRED
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'loss': F.cross_entropy(y_hat, y)(y_hat, y)}
+
+    def validation_step(self, batch, batch_nb):
+        # OPTIONAL
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'val_loss': F.cross_entropy(y_hat, y)(y_hat, y)}
+
+    def validation_end(self, outputs):
+        # OPTIONAL
+        avg_loss = torch.stack([x['val_loss'] for x in outputs]).mean()
+        return {'avg_val_loss': avg_loss}
+
+    def configure_optimizers(self):
+        # REQUIRED
+        return [torch.optim.Adam(self.parameters(), lr=0.02)]
+
+    @pl.data_loader
+    def tng_dataloader(self):
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+
+    @pl.data_loader
+    def val_dataloader(self):
+        # OPTIONAL
+        # can also return a list of val dataloaders
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+
+    @pl.data_loader
+    def test_dataloader(self):
+        # OPTIONAL
+        return DataLoader(MNIST(os.getcwd(), train=True, download=True, transform=transforms.ToTensor()), batch_size=32)
+```
+---   
+### How do these methods fit into the broader training?     
+The LightningModule interface is on the right. Each method corresponds to a part of a research project. Lightning automates everything not in blue.    
+
+<p align="center">
+  <a href="https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/overview_flat.jpg">
+    <img alt="" src="https://github.com/williamFalcon/pytorch-lightning/blob/master/docs/source/_static/overview_flat.jpg" height="900px">
+  </a>
+</p>   
+
+## Required Methods    
 
 ### training_step
 
@@ -72,15 +138,75 @@ def training_step(self, data_batch, batch_nb):
     return output
 ```
 
----
+--- 
+### tng_dataloader 
+
+``` {.python}
+@pl.data_loader
+def tng_dataloader(self)
+```
+Called by lightning during training loop. Make sure to use the @pl.data_loader decorator, this ensures not calling this function until the data are needed.
+
+##### Return
+PyTorch DataLoader
+
+**Example**
+
+``` {.python}
+@pl.data_loader
+def tng_dataloader(self):
+    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
+    dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True)
+    loader = torch.utils.data.DataLoader(
+        dataset=dataset,
+        batch_size=self.hparams.batch_size,
+        shuffle=True
+    )
+    return loader
+```
+
+--- 
+### configure_optimizers 
+
+``` {.python}
+def configure_optimizers(self)
+```
+
+Set up as many optimizers and (optionally) learning rate schedulers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. 
+Lightning will call .backward() and .step() on each one in every epoch.  If you use 16 bit precision it will also handle that.
+
+
+##### Return
+List or Tuple - List of optimizers with an optional second list of learning-rate schedulers
+
+**Example**
+
+``` {.python}
+# most cases
+def configure_optimizers(self):
+    opt = Adam(self.parameters(), lr=0.01)
+    return [opt]
+    
+# gan example, with scheduler for discriminator
+def configure_optimizers(self):
+    generator_opt = Adam(self.model_gen.parameters(), lr=0.01)
+    disriminator_opt = Adam(self.model_disc.parameters(), lr=0.02)
+    discriminator_sched = CosineAnnealing(discriminator_opt, T_max=10)
+    return [generator_opt, disriminator_opt], [discriminator_sched]
+```
+
+## Optional Methods    
 
 ### validation_step
 
 ``` {.python}
-def validation_step(self, data_batch, batch_nb)
+def validation_step(self, data_batch, batch_nb, dataloader_i)
 ```
+**OPTIONAL**    
+If you don't need to validate you don't need to implement this method.    
+
+In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes, calculate accuracy, or save example outputs (using self.experiment or whatever you want). Really, anything you want.       
 
-In this step you'd normally do the forward pass and calculate the loss for a batch. You can also do fancier things like multiple forward passes or something specific to your model.
 This is most likely the same as your training_step. But unlike training step, the outputs from here will go to validation_end for collation.
 
 **Params**   
@@ -89,6 +215,7 @@ This is most likely the same as your training_step. But unlike training step, th
 |---|---|
 |  data_batch | The output of your dataloader. A tensor, tuple or list  |
 |  batch_nb | Integer displaying which batch this is  |
+|  dataloader_i | Integer displaying which dataloader this is  |
 
 **Return**   
 
@@ -126,9 +253,12 @@ def validation_step(self, data_batch, batch_nb):
 
 ``` {.python}
 def validation_end(self, outputs)
-```
+```   
+If you didn't define a validation_step, this won't be called.       
 
-Called at the end of the validation loop with the output of each validation_step.
+Called at the end of the validation loop with the output of each validation_step.  Called once per validation dataset.   
+
+The outputs here are strictly for the progress bar. If you don't need to display anything, don't return anything.    
 
 **Params**    
 
@@ -164,63 +294,35 @@ def validation_end(self, outputs):
 ```
 
 --- 
-### configure_optimizers 
+### on_save_checkpoint 
 
 ``` {.python}
-def configure_optimizers(self)
+def on_save_checkpoint(self, checkpoint)
 ```
-
-Set up as many optimizers as you need. Normally you'd need one. But in the case of GANs or something more esoteric you might have multiple. 
-Lightning will call .backward() and .step() on each one.  If you use 16 bit precision it will also handle that.
-
+Called by lightning to checkpoint your model. Lightning saves the training state (current epoch, global_step, etc)
+and also saves the model state_dict. If you want to save anything else, use this method to add your own
+key-value pair.
 
 ##### Return
-List - List of optimizers
+Nothing
 
 **Example**
 
 ``` {.python}
-# most cases
-def configure_optimizers(self):
-    opt = Adam(lr=0.01)
-    return [opt]
-    
-# gan example
-def configure_optimizers(self):
-    generator_opt = Adam(lr=0.01)
-    disriminator_opt = Adam(lr=0.02)
-    return [generator_opt, disriminator_opt] 
+def on_save_checkpoint(self, checkpoint):
+    # 99% of use cases you don't need to implement this method 
+    checkpoint['something_cool_i_want_to_save'] = my_cool_pickable_object
 ```
 
 --- 
-### get_save_dict 
+### on_load_checkpoint 
 
 ``` {.python}
-def get_save_dict(self)
+def on_load_checkpoint(self, checkpoint)
 ```
-Called by lightning to checkpoint your model. Lightning saves current epoch, current batch nb, etc...
-All you have to return is what specifically about your lightning model you want to checkpoint.
-
-##### Return
-Dictionary - No required keys. Most of the time as described in this example.   
-
-**Example**
-
-``` {.python}
-def get_save_dict(self):
-    # 99% of use cases this is all you need to return
-    checkpoint = {'state_dict': self.state_dict()}
-    return checkpoint
-```
-
---- 
-### load_model_specific 
-
-``` {.python}
-def load_model_specific(self, checkpoint)
-```
-Called by lightning to restore your model. This is your chance to restore your model using the keys you added in get_save_dict.
-Lightning will automatically restore current epoch, batch nb, etc. 
+Called by lightning to restore your model. Lighting auto-restores global step, epoch, etc...
+It also restores the model state_dict.
+If you saved something with **on_save_checkpoint** this is your chance to restore this.
 
 ##### Return
 Nothing  
@@ -228,108 +330,76 @@ Nothing
 **Example**
 
 ``` {.python}
-def load_model_specific(self, checkpoint):
-    # you defined 'state_dict' in get_save_dict()
-    self.load_state_dict(checkpoint['state_dict'])
-```
-
---- 
-### tng_dataloader 
-
-``` {.python}
-@property
-def tng_dataloader(self)
-```
-Called by lightning during training loop. Define it as a property.
-
-##### Return
-Pytorch DataLoader
-
-**Example**
-
-``` {.python}
-@property
-def tng_dataloader(self):
-    if self._tng_dataloader is None:
-        try:
-            transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
-            dataset = MNIST(root='/path/to/mnist/', train=True, transform=transform, download=True)
-            loader = torch.utils.data.DataLoader(
-                dataset=dataset,
-                batch_size=self.hparams.batch_size,
-                shuffle=True
-            )
-            self._tng_dataloader = loader
-        except Exception as e:
-            raise e
-            
-    return self._tng_dataloader
+def on_load_checkpoint(self, checkpoint):
+    # 99% of the time you don't need to implement this method
+    self.something_cool_i_want_to_save = checkpoint['something_cool_i_want_to_save']
 ```
 
 --- 
 ### val_dataloader 
 
 ``` {.python}
-@property
+@pl.data_loader
 def tng_dataloader(self)
 ```
-Called by lightning during validation loop. Define it as a property.
+**OPTIONAL**    
+If you don't need a validation dataset and a validation_step, you don't need to implement this method.    
+
+Called by lightning during validation loop. Make sure to use the @pl.data_loader decorator, this ensures not calling this function until the data are needed.   
 
 ##### Return
-Pytorch DataLoader
+PyTorch DataLoader or list of PyTorch Dataloaders.    
 
 **Example**
 
 ``` {.python}
-@property
+@pl.data_loader
 def val_dataloader(self):
-    if self._val_dataloader is None:
-        try:
-            transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
-            dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True)
-            loader = torch.utils.data.DataLoader(
-                dataset=dataset,
-                batch_size=self.hparams.batch_size,
-                shuffle=True
-            )
-            self._val_dataloader = loader
-        except Exception as e:
-            raise e
-            
-    return self._val_dataloader
+    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
+    dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True)
+    loader = torch.utils.data.DataLoader(
+        dataset=dataset,
+        batch_size=self.hparams.batch_size,
+        shuffle=True
+    )
+    
+    return loader
+
+# can also return multiple dataloaders   
+@pl.data_loader
+def val_dataloader(self):
+    return [loader_a, loader_b, ..., loader_n]   
 ```
 
 --- 
 ### test_dataloader 
 
 ``` {.python}
-@property
+@pl.data_loader
 def test_dataloader(self)
 ```
-Called by lightning during test loop. Define it as a property.
+**OPTIONAL**    
+If you don't need a test dataset and a test_step, you don't need to implement this method.    
+
+Called by lightning during test loop. Make sure to use the @pl.data_loader decorator, this ensures not calling this function until the data are needed.
 
 ##### Return
-Pytorch DataLoader
+PyTorch DataLoader
 
 **Example**
 
 ``` {.python}
-@property
+@pl.data_loader
 def test_dataloader(self):
-    if self._test_dataloader is None:
-        try:
-            transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
-            dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True)
-            loader = torch.utils.data.DataLoader(
-                dataset=dataset,
-                batch_size=self.hparams.batch_size,
-                shuffle=True
-            )
-            self._test_dataloader = loader
-        except Exception as e:
-            raise e
-            
-    return self._test_dataloader
+    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
+    dataset = MNIST(root='/path/to/mnist/', train=False, transform=transform, download=True)
+    loader = torch.utils.data.DataLoader(
+        dataset=dataset,
+        batch_size=self.hparams.batch_size,
+        shuffle=True
+    )
+    
+    return loader
 ```
 
 --- 
@@ -391,4 +461,4 @@ def add_model_specific_args(parent_parser, root_dir):
     parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False)
     parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
     return parser
-```
+```

docs/LightningModule/methods.md

@@ -21,7 +21,8 @@ pretrained_model = MyLightningModule.load_from_metrics(
     map_location=None
 )
     
-# predict 
+# predict
+pretrained_model.eval()
 pretrained_model.freeze()
 y_hat = pretrained_model(x)
 ```
@@ -30,7 +31,7 @@ y_hat = pretrained_model(x)
 
 | Param  | description  |
 |---|---|
-|  weights_path | Path to a pytorch checkpoint  |
+|  weights_path | Path to a PyTorch checkpoint  |
 |  tags_csv | Path to meta_tags.csv file generated by the test-tube Experiment  |
 |  on_gpu | if True, puts model on GPU. Make sure to use transforms option if model devices have changed  |
 |  map_location | A dictionary mapping saved weight GPU devices to new GPU devices |

docs/LightningModule/properties.md

@@ -38,3 +38,17 @@ self.trainer.current_epoch
 ...   
 ```   
 
+## Debugging   
+The LightningModule also offers these tricks to help debug.   
+
+---   
+#### example_input_array    
+In the LightningModule init, you can set a dummy tensor for this property
+to get a print out of sizes coming into and out of every layer.   
+```python
+def __init__(self):
+    # put the dimensions of the first input to your system
+    self.example_input_array = torch.rand(5, 28 * 28)
+```    
+
+

docs/Trainer/Checkpointing.md

@@ -1,11 +1,11 @@
-Lightning can automate saving and loading checkpoints.
+i Lightning can automate saving and loading checkpoints.
 
 ---
 ### Model saving
 To enable checkpointing, define the checkpoint callback and give it to the trainer.
 
 ``` {.python}
-from pytorch_lightning.utils.pt_callbacks import ModelCheckpoint
+from pytorch_lightning.callbacks import ModelCheckpoint
 
 checkpoint_callback = ModelCheckpoint(
     filepath='/path/to/store/weights.ckpt',
@@ -18,5 +18,51 @@ checkpoint_callback = ModelCheckpoint(
 trainer = Trainer(checkpoint_callback=checkpoint_callback)
 ```
 
+---
+### Restoring training session 
+You might want to not only load a model but also continue training it. Use this method to
+restore the trainer state as well. This will continue from the epoch and global step you last left off.  
+However, the dataloaders will start from the first batch again (if you shuffled it shouldn't matter).   
 
+Lightning will restore the session if you pass an experiment with the same version and there's a saved checkpoint.   
+``` {.python}
+from test_tube import Experiment
 
+exp = Experiment(version=a_previous_version_with_a_saved_checkpoint)
+trainer = Trainer(experiment=exp)
+
+# this fit call loads model weights and trainer state
+# the trainer continues seamlessly from where you left off
+# without having to do anything else.
+trainer.fit(model)
+```
+
+The trainer restores:  
+- global_step    
+- current_epoch    
+- All optimizers    
+- All lr_schedulers    
+- Model weights
+
+You can even change the logic of your model as long as the weights and "architecture" of 
+the system isn't different. If you add a layer, for instance, it might not work.   
+
+At a rough level, here's [what happens inside Trainer](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/root_module/model_saving.py#L63):   
+```python
+
+self.global_step = checkpoint['global_step']
+self.current_epoch = checkpoint['epoch']
+
+# restore the optimizers
+optimizer_states = checkpoint['optimizer_states']
+for optimizer, opt_state in zip(self.optimizers, optimizer_states):
+    optimizer.load_state_dict(opt_state)
+
+# restore the lr schedulers
+lr_schedulers = checkpoint['lr_schedulers']
+for scheduler, lrs_state in zip(self.lr_schedulers, lr_schedulers):
+    scheduler.load_state_dict(lrs_state)
+
+# uses the model you passed into trainer        
+model.load_state_dict(checkpoint['state_dict'])
+```    

docs/Trainer/Distributed training.md

@@ -3,6 +3,52 @@ Lightning makes multi-gpu training and 16 bit training trivial.
 *Note:*   
 None of the flags below require changing anything about your lightningModel definition. 
 
+---
+#### Choosing a backend  
+Lightning supports two backends. DataParallel and DistributedDataParallel. Both can be used for single-node multi-GPU training.
+For multi-node training you must use DistributedDataParallel.   
+
+You can toggle between each mode by setting this flag.
+``` {.python}
+# DEFAULT uses DataParallel
+trainer = Trainer(distributed_backend='dp')
+
+# change to distributed data parallel
+trainer = Trainer(distributed_backend='ddp')
+```
+
+If you request multiple nodes, the back-end will auto-switch to ddp.
+We recommend you use DistributedDataparallel even for single-node multi-GPU training. It is MUCH faster than DP but *may*
+have configuration issues depending on your cluster.
+
+For a deeper understanding of what lightning is doing, feel free to read [this guide](https://medium.com/@_willfalcon/9-tips-for-training-lightning-fast-neural-networks-in-pytorch-8e63a502f565).   
+
+---
+#### Distributed and 16-bit precision.    
+Due to an issue with apex and DistributedDataParallel (PyTorch and NVIDIA issue), Lightning does
+not allow 16-bit and DP training. We tried to get this to work, but it's an issue on their end.   
+
+Below are the possible configurations we support.    
+
+| 1 GPU  | 1+ GPUs  | DP  | DDP  | 16-bit  | command |
+|---|---|---|---|---|---|
+| Y  |   |   |   |  | ```Trainer(gpus=[0])``` |
+| Y  |   |   |   | Y | ```Trainer(gpus=[0], use_amp=True)``` |
+|   | Y | Y |   |   | ```Trainer(gpus=[0, ...])``` |
+|   | Y |  | Y  |  | ```Trainer(gpus=[0, ...], distributed_backend='ddp')``` |
+|   | Y |  | Y  | Y | ```Trainer(gpus=[0, ...], distributed_backend='ddp', use_amp=True)``` |
+
+
+---
+#### CUDA flags   
+CUDA flags make certain GPUs visible to your script. 
+Lightning sets these for you automatically, there's NO NEED to do this yourself.
+```python
+# lightning will set according to what you give the trainer
+# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+```
+
 ---
 #### 16-bit mixed precision
 16 bit precision can cut your memory footprint by half. If using volta architecture GPUs it can give a dramatic training speed-up as well.    
@@ -23,10 +69,6 @@ trainer = Trainer(amp_level='O2', use_amp=False)
 #### Single-gpu
 Make sure you're on a GPU machine. 
 ```python
-# set these flags
-os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
-os.environ["CUDA_VISIBLE_DEVICES"] = "0"
-
 # DEFAULT
 trainer = Trainer(gpus=[0])
 ```
@@ -36,17 +78,63 @@ trainer = Trainer(gpus=[0])
 Make sure you're on a GPU machine. You can set as many GPUs as you want.
 In this setting, the model will run on all 8 GPUs at once using DataParallel under the hood.
 ```python
-# set these flags
-os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
-os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2,3,4,5,6,7"
+# to use DataParallel (default)
+trainer = Trainer(gpus=[0,1,2,3,4,5,6,7], distributed_backend='dp')
 
-# DEFAULT
-trainer = Trainer(gpus=[0,1,2,3,4,5,6,7])
+# RECOMMENDED use DistributedDataParallel
+trainer = Trainer(gpus=[0,1,2,3,4,5,6,7], distributed_backend='ddp')
 ```
 
 ---
 #### Multi-node
-COMING SOON.
+Multi-node training is easily done by specifying these flags.
+```python
+# train on 12*8 GPUs
+trainer = Trainer(gpus=[0,1,2,3,4,5,6,7], nb_gpu_nodes=12)
+```
+
+In addition, make sure to set up your SLURM job correctly via the [SlurmClusterObject](https://williamfalcon.github.io/test-tube/hpc/SlurmCluster/). In particular, specify the number of tasks per node correctly.
+
+```python
+cluster = SlurmCluster(
+    hyperparam_optimizer=test_tube.HyperOptArgumentParser(),
+    log_path='/some/path/to/save',
+)
+
+# OPTIONAL FLAGS WHICH MAY BE CLUSTER DEPENDENT
+# which interface your nodes use for communication
+cluster.add_command('export NCCL_SOCKET_IFNAME=^docker0,lo')
+
+# see output of the NCCL connection process
+# NCCL is how the nodes talk to each other
+cluster.add_command('export NCCL_DEBUG=INFO')
+
+# setting a master port here is a good idea.
+cluster.add_command('export MASTER_PORT=%r' % PORT)
+
+# good to load the latest NCCL version
+cluster.load_modules(['NCCL/2.4.7-1-cuda.10.0'])
+
+# configure cluster
+cluster.per_experiment_nb_nodes = 12 
+cluster.per_experiment_nb_gpus = 8
+
+cluster.add_slurm_cmd(cmd='ntasks-per-node', value=8, comment='1 task per gpu')
+```
+
+Finally, make sure to add a distributed sampler to your dataset. The distributed sampler copies a 
+portion of your dataset onto each GPU. (World_size = gpus_per_node * nb_nodes).   
+
+```python
+# ie: this:
+dataset = myDataset()
+dataloader = Dataloader(dataset)
+
+# becomes:
+dataset = myDataset()
+dist_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
+dataloader = Dataloader(dataset, sampler=dist_sampler)
+```
 
 ---
 #### Self-balancing architecture

docs/Trainer/Logging.md

@@ -33,7 +33,7 @@ trainer = Trainer(process_position=1)
 Whenever you call .save() on the test-tube experiment it logs all the hyperparameters in current use.
 Give lightning a test-tube Experiment object to automate this for you.
 ``` {.python}
-from test-tube import Experiment
+from test_tube import Experiment
 
 exp = Experiment(...)
 Trainer(experiment=exp)
@@ -44,12 +44,48 @@ Trainer(experiment=exp)
 Whenever you call .save() on the test-tube experiment it snapshows all code and pushes to a git tag.
 Give lightning a test-tube Experiment object to automate this for you.
 ``` {.python}
-from test-tube import Experiment
+from test_tube import Experiment
 
 exp = Experiment(create_git_tag=True)
 Trainer(experiment=exp)
 ```
 
+---
+### Tensorboard support   
+In the LightningModule you can access the experiment logger by doing:
+```python
+self.experiment
+
+# add image
+# Look at PyTorch SummaryWriter docs for what you can do.   
+self.experiment.add_image(...)
+```
+
+The experiment object is a strict subclass of PyTorch SummaryWriter. However, this class
+also snapshots every detail about the experiment (data folder paths, code, hyperparams),
+and allows you to visualize it using tensorboard.
+``` {.python}
+from test_tube import Experiment, HyperOptArgumentParser
+
+# exp hyperparams
+args = HyperOptArgumentParser()
+hparams = args.parse_args()
+
+# this is a summaryWriter with nicer logging structure
+exp = Experiment(save_dir='/some/path', create_git_tag=True)
+
+# track experiment details (must be ArgumentParser or HyperOptArgumentParser).
+# each option in the parser is tracked
+exp.argparse(hparams)
+exp.tag({'description': 'running demo'})
+
+# trainer uses the exp object to log exp data
+trainer = Trainer(experiment=exp)
+trainer.fit(model)
+
+# view logs at:
+# tensorboard --logdir /some/path   
+```
 
 ---
 #### Write logs file to csv every k batches 

docs/Trainer/Training Loop.md

@@ -1,4 +1,4 @@
-The lightning training loop handles everything except the actual computations of your model. To decide what will happen in your training loop, define the [training_step function](../../Pytorch-lightning/LightningModule/#training_step).
+The lightning training loop handles everything except the actual computations of your model. To decide what will happen in your training loop, define the [training_step function](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#training_step).
 
 Below are all the things lightning automates for you in the training loop.
 
@@ -11,17 +11,6 @@ Accumulated gradients runs K small batches of size N before doing a backwards pa
 trainer = Trainer(accumulate_grad_batches=1)
 ```
 
----
-#### Anneal Learning rate
-Cut the learning rate by 10 at every epoch listed in this list.
-``` {.python}
-# DEFAULT (don't anneal)
-trainer = Trainer(lr_scheduler_milestones=None)
-
-# cut LR by 10 at 100, 200, and 300 epochs 
-trainer = Trainer(lr_scheduler_milestones=[100, 200, 300])
-```
-
 ---
 #### Force training for min or max epochs
 It can be useful to force training for a minimum number of epochs or limit to a max number
@@ -39,15 +28,18 @@ trainer = Trainer(enable_early_stop=True)
 ```
 
 ---
-#### Gradient Clipping 
-Use this to turn off early stopping and run training to the [max_epoch](#force-training-for-min-or-max-epochs)
+#### Gradient Clipping
+Gradient clipping may be enabled to avoid exploding gradients.
+Specifically, this will [clip the gradient norm computed over all model parameters *together*](https://pytorch.org/docs/stable/nn.html#torch.nn.utils.clip_grad_norm_).
+
 ``` {.python}
 # DEFAULT (ie: don't clip)
 trainer = Trainer(gradient_clip=0)
+
+# clip gradients with norm above 0.5
+trainer = Trainer(gradient_clip=0.5)
 ```
 
-
-
 ---
 #### Inspect gradient norms
 Looking at grad norms can help you figure out where training might be going wrong.

docs/Trainer/Validation loop.md

@@ -1,4 +1,4 @@
-The lightning validation loop handles everything except the actual computations of your model. To decide what will happen in your validation loop, define the [validation_step function](../../Pytorch-lightning/LightningModule/#validation_step).
+The lightning validation loop handles everything except the actual computations of your model. To decide what will happen in your validation loop, define the [validation_step function](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#validation_step).
 Below are all the things lightning automates for you in the validation loop.
 
 **Note**   

docs/Trainer/hooks.md

@@ -0,0 +1,94 @@
+# Hooks
+[[Github Code](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/root_module/hooks.py)]   
+
+There are cases when you might want to do something different at different parts of the training/validation loop.
+To enable a hook, simply override the method in your LightningModule and the trainer will call it at the correct time.
+
+**Contributing** If there's a hook you'd like to add, simply:    
+1. Fork PyTorchLightning.    
+2. Add the hook [here](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/root_module/hooks.py).       
+3. Add the correct place in the [Trainer](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/models/trainer.py) where it should be called.    
+
+---
+#### on_epoch_start
+Called in the training loop at the very beginning of the epoch.   
+```python
+def on_epoch_start(self):
+    # do something when the epoch starts
+```
+
+---
+#### on_epoch_end
+Called in the training loop at the very end of the epoch.   
+```python
+def on_epoch_end(self):
+    # do something when the epoch ends 
+```
+
+---
+#### on_batch_start
+Called in the training loop before anything happens for that batch.   
+```python
+def on_batch_start(self):
+    # do something when the batch starts
+```
+
+---
+#### on_batch_end
+Called in the training loop after the batch.   
+```python
+def on_batch_end(self):
+    # do something when the batch ends 
+```
+
+---
+#### on_pre_performance_check
+Called at the very beginning of the validation loop.   
+```python
+def on_pre_performance_check(self):
+    # do something before validation starts 
+```
+
+---
+#### on_post_performance_check
+Called at the very end of the validation loop.   
+```python
+def on_post_performance_check(self):
+    # do something before validation end
+```
+
+---
+#### on_tng_metrics
+Called in the training loop, right before metrics are logged.
+Although you can log at any time by using self.experiment, you can use
+this callback to modify what will be logged.
+```python
+def on_tng_metrics(self, metrics):
+    # do something before validation end
+```
+
+---
+#### on_before_zero_grad
+Called in the training loop after taking an optimizer step and before zeroing grads.
+Good place to inspect weight information with weights updated.
+
+Called once per optimizer
+```python
+def on_before_zero_grad(self, optimizer):
+    # do something with the optimizer or inspect it. 
+```
+
+---
+#### on_after_backward
+Called in the training loop after model.backward()
+This is the ideal place to inspect or log gradient information 
+```python
+def on_after_backward(self):
+    # example to inspect gradient information in tensorboard
+    if self.trainer.global_step % 25 == 0:  # don't make the tf file huge
+        params = self.state_dict()
+        for k, v in params.items():
+            grads = v
+            name = k
+            self.experiment.add_histogram(tag=name, values=grads, global_step=self.trainer.global_step)
+```

docs/Trainer/index.md

@@ -19,56 +19,61 @@ But of course the fun is in all the advanced things it can do:
 
 **Checkpointing**    
 
-- Model saving
-- Model loading 
+- [Model saving](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#model-saving)
+- [Model loading](https://williamfalcon.github.io/pytorch-lightning/LightningModule/methods/#load-from-metrics) 
+- [Restoring training session](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#restoring-training-session)
 
 **Computing cluster (SLURM)**    
 
-- [Running grid search on a cluster](SLURM%20Managed%20Cluster/#running-grid-search-on-a-cluster)
-- [Walltime auto-resubmit](SLURM%20Managed%20Cluster/#walltime-auto-resubmit)   
+- [Running grid search on a cluster](https://williamfalcon.github.io/pytorch-lightning/Trainer/SLURM%20Managed%20Cluster#running-grid-search-on-a-cluster) 
+- [Walltime auto-resubmit](https://williamfalcon.github.io/pytorch-lightning/Trainer/SLURM%20Managed%20Cluster#walltime-auto-resubmit)   
 
 **Debugging**  
 
-- [Fast dev run](Debugging/#fast-dev-run)
-- [Inspect gradient norms](Debugging/#inspect-gradient-norms)
-- [Log GPU usage](Debugging/#Log-gpu-usage)
-- [Make model overfit on subset of data](Debugging/#make-model-overfit-on-subset-of-data)
-- [Print the parameter count by layer](Debugging/#print-the-parameter-count-by-layer)
-- [Pring which gradients are nan](Debugging/#print-which-gradients-are-nan)
+- [Fast dev run](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#fast-dev-run)
+- [Inspect gradient norms](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#inspect-gradient-norms)
+- [Log GPU usage](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#Log-gpu-usage)
+- [Make model overfit on subset of data](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#make-model-overfit-on-subset-of-data)
+- [Print the parameter count by layer](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-the-parameter-count-by-layer)
+- [Pring which gradients are nan](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-which-gradients-are-nan)
+- [Print input and output size of every module in system](https://williamfalcon.github.io/pytorch-lightning/LightningModule/properties/#example_input_array)
 
 
 **Distributed training**    
 
-- [16-bit mixed precision](Distributed%20training/#16-bit-mixed-precision)
-- [Multi-GPU](Distributed%20training/#Multi-GPU)
-- [Multi-node](Distributed%20training/#Multi-node)
-- [Single GPU](Distributed%20training/#single-gpu)
-- [Self-balancing architecture](Distributed%20training/#self-balancing-architecture)
+- [16-bit mixed precision](https://williamfalcon.github.io/pytorch-lightning/Trainer/Distributed%20training/#16-bit-mixed-precision)
+- [Multi-GPU](https://williamfalcon.github.io/pytorch-lightning/Trainer/Distributed%20training/#Multi-GPU)
+- [Multi-node](https://williamfalcon.github.io/pytorch-lightning/Trainer/Distributed%20training/#Multi-node)
+- [Single GPU](https://williamfalcon.github.io/pytorch-lightning/Trainer/Distributed%20training/#single-gpu)
+- [Self-balancing architecture](https://williamfalcon.github.io/pytorch-lightning/Trainer/Distributed%20training/#self-balancing-architecture)
 
 
 **Experiment Logging**   
 
-- [Display metrics in progress bar](Logging/#display-metrics-in-progress-bar)
-- Log arbitrary metrics
-- [Log metric row every k batches](Logging/#log-metric-row-every-k-batches)
-- [Process position](Logging/#process-position)
-- [Save a snapshot of all hyperparameters](Logging/#save-a-snapshot-of-all-hyperparameters) 
-- [Snapshot code for a training run](Logging/#snapshot-code-for-a-training-run) 
-- [Write logs file to csv every k batches](Logging/#write-logs-file-to-csv-every-k-batches)
+- [Display metrics in progress bar](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#display-metrics-in-progress-bar)
+- [Log metric row every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#log-metric-row-every-k-batches)
+- [Process position](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#process-position)
+- [Tensorboard support](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#tensorboard-support)
+- [Save a snapshot of all hyperparameters](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#save-a-snapshot-of-all-hyperparameters) 
+- [Snapshot code for a training run](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#snapshot-code-for-a-training-run) 
+- [Write logs file to csv every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#write-logs-file-to-csv-every-k-batches)
 
 **Training loop**    
 
-- [Accumulate gradients](Training%20Loop/#accumulated-gradients)
-- [Anneal Learning rate](Training%20Loop/#anneal-learning-rate)
-- [Force training for min or max epochs](Training%20Loop/#force-training-for-min-or-max-epochs)
-- [Force disable early stop](Training%20Loop/#force-disable-early-stop)
-- [Use multiple optimizers (like GANs)](../Pytorch-lightning/LightningModule/#configure_optimizers)
-- [Set how much of the training set to check (1-100%)](Training%20Loop/#set-how-much-of-the-training-set-to-check)
+- [Accumulate gradients](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#accumulated-gradients)
+- [Force training for min or max epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-training-for-min-or-max-epochs)
+- [Force disable early stop](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-disable-early-stop)
+- [Gradient Clipping](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#gradient-clipping)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
+- [Learning rate scheduling](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)
+- [Use multiple optimizers (like GANs)](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)
+- [Set how much of the training set to check (1-100%)](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#set-how-much-of-the-training-set-to-check)
 
 **Validation loop**    
 
-- [Check validation every n epochs](Validation%20Loop/#check-validation-every-n-epochs)
-- [Set how much of the validation set to check](Validation%20Loop/#set-how-much-of-the-validation-set-to-check)
-- [Set how much of the test set to check](Validation%20Loop/#set-how-much-of-the-test-set-to-check)
-- [Set validation check frequency within 1 training epoch](Validation%20Loop/#set-validation-check-frequency-within-1-training-epoch)
-- [Set the number of validation sanity steps](Validation%20Loop/#set-the-number-of-validation-sanity-steps)
+- [Check validation every n epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#check-validation-every-n-epochs)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
+- [Set how much of the validation set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-validation-set-to-check)
+- [Set how much of the test set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-test-set-to-check)
+- [Set validation check frequency within 1 training epoch](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-validation-check-frequency-within-1-training-epoch)
+- [Set the number of validation sanity steps](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-the-number-of-validation-sanity-steps)

docs/examples/Examples.md

@@ -3,7 +3,7 @@ In 99% of cases you want to just copy [this template](https://github.com/william
 
 ```bash
 # get a copy of the module template
-wget https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/lightning_module_template.py
+wget https://raw.githubusercontent.com/williamFalcon/pytorch-lightning/master/examples/new_project_templates/lightning_module_template.py
 ```
 
 ---    

docs/index.md

@@ -1,10 +1,17 @@
 ###### New project Quick Start    
-To start a new project define these two files.   
+To start a new project you define two files, a LightningModule and a Trainer file.    
 
-1. [Define a LightningModule](/LightningModule/RequiredTrainerInterface/#template-model-definition)  
-2. Pick a trainer      
-    - [Basic CPU Trainer](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/trainer_cpu_template.py) 
-    - [GPU cluster Trainer](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/trainer_gpu_cluster_template.py)
+A separate trainer file allows to run many LightningModules. Each LightningModule has the core
+logic to a particular research project.    
+
+For example, one lightningModule could be an image classifier, the other
+one could be a seq-2-seq model, both (optionally) ran by the same trainer file.
+
+1. [MNIST LightningModule](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#minimal-example) 
+2. [Trainer](https://williamfalcon.github.io/pytorch-lightning/Trainer/)
+    - [Basic CPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/single_cpu_template.py) 
+    - [Multi-GPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/single_gpu_node_template.py)
+    - [GPU cluster Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/multi_node_cluster_template.py)
 
 ###### Docs shortcuts
 - [LightningModule](LightningModule/RequiredTrainerInterface/)  
@@ -21,6 +28,7 @@ To start a new project define these two files.
 
 - [Model saving](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#model-saving)
 - [Model loading](https://williamfalcon.github.io/pytorch-lightning/LightningModule/methods/#load-from-metrics) 
+- [Restoring training session](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#restoring-training-session)
 
 ###### Computing cluster (SLURM)    
 
@@ -35,6 +43,7 @@ To start a new project define these two files.
 - [Make model overfit on subset of data](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#make-model-overfit-on-subset-of-data)
 - [Print the parameter count by layer](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-the-parameter-count-by-layer)
 - [Pring which gradients are nan](https://williamfalcon.github.io/pytorch-lightning/Trainer/debugging/#print-which-gradients-are-nan)
+- [Print input and output size of every module in system](https://williamfalcon.github.io/pytorch-lightning/LightningModule/properties/#example_input_array)
 
 
 ###### Distributed training    
@@ -49,9 +58,9 @@ To start a new project define these two files.
 ###### Experiment Logging   
 
 - [Display metrics in progress bar](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#display-metrics-in-progress-bar)
-- Log arbitrary metrics
 - [Log metric row every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#log-metric-row-every-k-batches)
 - [Process position](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#process-position)
+- [Tensorboard support](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#tensorboard-support)
 - [Save a snapshot of all hyperparameters](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#save-a-snapshot-of-all-hyperparameters) 
 - [Snapshot code for a training run](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#snapshot-code-for-a-training-run) 
 - [Write logs file to csv every k batches](https://williamfalcon.github.io/pytorch-lightning/Trainer/Logging/#write-logs-file-to-csv-every-k-batches)
@@ -59,16 +68,18 @@ To start a new project define these two files.
 ###### Training loop    
 
 - [Accumulate gradients](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#accumulated-gradients)
-- [Anneal Learning rate](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#anneal-learning-rate)
 - [Force training for min or max epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-training-for-min-or-max-epochs)
 - [Force disable early stop](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#force-disable-early-stop)
 - [Gradient Clipping](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#gradient-clipping)
-- [Use multiple optimizers (like GANs)](https://williamfalcon.github.io/pytorch-lightning/Pytorch-Lightning/LightningModule/#configure_optimizers)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
+- [Learning rate scheduling](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)
+- [Use multiple optimizers (like GANs)](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#configure_optimizers)
 - [Set how much of the training set to check (1-100%)](https://williamfalcon.github.io/pytorch-lightning/Trainer/Training%20Loop/#set-how-much-of-the-training-set-to-check)
 
-######Validation loop    
+###### Validation loop    
 
 - [Check validation every n epochs](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#check-validation-every-n-epochs)
+- [Hooks](https://williamfalcon.github.io/pytorch-lightning/Trainer/hooks/)
 - [Set how much of the validation set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-validation-set-to-check)
 - [Set how much of the test set to check](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-how-much-of-the-test-set-to-check)
 - [Set validation check frequency within 1 training epoch](https://williamfalcon.github.io/pytorch-lightning/Trainer/Validation%20loop/#set-validation-check-frequency-within-1-training-epoch)

docs/requirements.txt

@@ -0,0 +1,2 @@
+mkdocs-material==4.4.0
+mkdocs==1.0.4

docs/source/_static/coverage.svg

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" width="99" height="20">
+    <linearGradient id="b" x2="0" y2="100%">
+        <stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
+        <stop offset="1" stop-opacity=".1"/>
+    </linearGradient>
+    <mask id="a">
+        <rect width="99" height="20" rx="3" fill="#fff"/>
+    </mask>
+    <g mask="url(#a)">
+        <path fill="#555" d="M0 0h63v20H0z"/>
+        <path fill="#4c1" d="M63 0h36v20H63z"/>
+        <path fill="url(#b)" d="M0 0h99v20H0z"/>
+    </g>
+    <g fill="#fff" text-anchor="middle" font-family="DejaVu Sans,Verdana,Geneva,sans-serif" font-size="11">
+        <text x="31.5" y="15" fill="#010101" fill-opacity=".3">coverage</text>
+        <text x="31.5" y="14">coverage</text>
+        <text x="80" y="15" fill="#010101" fill-opacity=".3">99%</text>
+        <text x="80" y="14">99%</text>
+    </g>
+</svg>

examples/__init__.py

@@ -0,0 +1,5 @@
+from .new_project_templates.lightning_module_template import LightningTemplateModel
+
+__all__ = [
+    'LightningTemplateModel'
+]

examples/new_project_templates/__init__.py

@@ -1 +0,0 @@
-from .lightning_module_template import LightningTemplateModel

examples/new_project_templates/lightning_module_template.py

@@ -1,3 +1,6 @@
+"""
+Example template for defining a system
+"""
 import os
 from collections import OrderedDict
 import torch.nn as nn
@@ -7,7 +10,10 @@ import torch
 import torch.nn.functional as F
 from test_tube import HyperOptArgumentParser
 from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.distributed import DistributedSampler
 
+import pytorch_lightning as pl
 from pytorch_lightning.root_module.root_module import LightningModule
 
 
@@ -22,10 +28,14 @@ class LightningTemplateModel(LightningModule):
         :param hparams:
         """
         # init superclass
-        super(LightningTemplateModel, self).__init__(hparams)
+        super(LightningTemplateModel, self).__init__()
+        self.hparams = hparams
 
         self.batch_size = hparams.batch_size
 
+        # if you specify an example input, the summary will show input/output for each layer
+        self.example_input_array = torch.rand(5, 28 * 28)
+
         # build model
         self.__build_model()
 
@@ -37,11 +47,13 @@ class LightningTemplateModel(LightningModule):
         Layout model
         :return:
         """
-        self.c_d1 = nn.Linear(in_features=self.hparams.in_features, out_features=self.hparams.hidden_dim)
+        self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+                              out_features=self.hparams.hidden_dim)
         self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
         self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
 
-        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim, out_features=self.hparams.out_features)
+        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+                              out_features=self.hparams.out_features)
 
     # ---------------------
     # TRAINING
@@ -76,18 +88,24 @@ class LightningTemplateModel(LightningModule):
         # forward pass
         x, y = data_batch
         x = x.view(x.size(0), -1)
+
         y_hat = self.forward(x)
 
         # calculate loss
         loss_val = self.loss(y, y_hat)
 
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+
         output = OrderedDict({
-            'loss': loss_val,
-            'tqdm_metrics': {}
+            'loss': loss_val
         })
+
+        # can also return just a scalar instead of a dict (return loss_val)
         return output
 
-    def validation_step(self, data_batch, batch_i):
+    def validation_step(self, data_batch, batch_i, dataloader_i):
         """
         Lightning calls this inside the validation loop
         :param data_batch:
@@ -102,11 +120,22 @@ class LightningTemplateModel(LightningModule):
         # acc
         labels_hat = torch.argmax(y_hat, dim=1)
         val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+        val_acc = torch.tensor(val_acc)
+
+        if self.on_gpu:
+            val_acc = val_acc.cuda(loss_val.device.index)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+            val_acc = val_acc.unsqueeze(0)
 
         output = OrderedDict({
             'val_loss': loss_val,
-            'val_acc': torch.tensor(val_acc),
+            'val_acc': val_acc,
         })
+
+        # can also return just a scalar instead of a dict (return loss_val)
         return output
 
     def validation_end(self, outputs):
@@ -115,31 +144,32 @@ class LightningTemplateModel(LightningModule):
         :param outputs: list of individual outputs of each validation step
         :return:
         """
+        # if returned a scalar from validation_step, outputs is a list of tensor scalars
+        # we return just the average in this case (if we want)
+        # return torch.stack(outputs).mean()
+
         val_loss_mean = 0
         val_acc_mean = 0
         for output in outputs:
-            val_loss_mean += output['val_loss']
-            val_acc_mean += output['val_acc']
+            val_loss = output['val_loss']
+
+            # reduce manually when using dp
+            if self.trainer.use_dp:
+                val_loss = torch.mean(val_loss)
+            val_loss_mean += val_loss
+
+            # reduce manually when using dp
+            val_acc = output['val_acc']
+            if self.trainer.use_dp:
+                val_acc_mean = torch.mean(val_acc)
+
+            val_acc_mean += val_acc_mean
 
         val_loss_mean /= len(outputs)
         val_acc_mean /= len(outputs)
-        tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()}
+        tqdm_dic = {'val_loss': val_loss_mean, 'val_acc': val_acc_mean}
         return tqdm_dic
 
-    def update_tng_log_metrics(self, logs):
-        return logs
-
-    # ---------------------
-    # MODEL SAVING
-    # ---------------------
-    def get_save_dict(self):
-        checkpoint = {'state_dict': self.state_dict()}
-        return checkpoint
-
-    def load_model_specific(self, checkpoint):
-        self.load_state_dict(checkpoint['state_dict'])
-        pass
-
     # ---------------------
     # TRAINING SETUP
     # ---------------------
@@ -149,54 +179,54 @@ class LightningTemplateModel(LightningModule):
         :return: list of optimizers
         """
         optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
-        return [optimizer]
+        scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
+        return [optimizer], [scheduler]
 
     def __dataloader(self, train):
         # init data generators
-        transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
+        transform = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize((0.5,), (1.0,))])
+        dataset = MNIST(root=self.hparams.data_root, train=train,
+                        transform=transform, download=True)
 
-        dataset = MNIST(root=self.hparams.data_root, train=train, transform=transform, download=True)
+        # when using multi-node we need to add the datasampler
+        train_sampler = None
+        batch_size = self.hparams.batch_size
 
-        loader = torch.utils.data.DataLoader(
+        try:
+            if self.on_gpu:
+                train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
+                batch_size = batch_size // self.trainer.world_size  # scale batch size
+        except Exception:
+            pass
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
             dataset=dataset,
-            batch_size=self.hparams.batch_size,
-            shuffle=True
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler
         )
 
         return loader
 
-    @property
+    @pl.data_loader
     def tng_dataloader(self):
-        if self._tng_dataloader is None:
-            try:
-                self._tng_dataloader = self.__dataloader(train=True)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._tng_dataloader
+        print('tng data loader called')
+        return self.__dataloader(train=True)
 
-    @property
+    @pl.data_loader
     def val_dataloader(self):
-        if self._val_dataloader is None:
-            try:
-                self._val_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._val_dataloader
+        print('val data loader called')
+        return [self.__dataloader(train=False) for i in range(2)]
 
-    @property
+    @pl.data_loader
     def test_dataloader(self):
-        if self._test_dataloader is None:
-            try:
-                self._test_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._test_dataloader
+        print('test data loader called')
+        return self.__dataloader(train=False)
 
     @staticmethod
-    def add_model_specific_args(parent_parser, root_dir):
+    def add_model_specific_args(parent_parser, root_dir):  # pragma: no cover
         """
         Parameters you define here will be available to your model through self.hparams
         :param parent_parser:
@@ -209,17 +239,25 @@ class LightningTemplateModel(LightningModule):
         # parser.set_defaults(gradient_clip=5.0)
 
         # network params
+        parser.add_argument('--in_features', default=28 * 28, type=int)
+        parser.add_argument('--out_features', default=10, type=int)
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
         parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
-        parser.add_argument('--in_features', default=28*28)
-        parser.add_argument('--out_features', default=10)
-        parser.add_argument('--hidden_dim', default=50000) # use 500 for CPU, 50000 for GPU to see speed difference
 
         # data
         parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
 
         # training params (opt)
-        parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
+        parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+                        options=[0.0001, 0.0005, 0.001, 0.005],
                         tunable=False)
-        parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False)
-        parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
+        parser.opt_list('--optimizer_name', default='adam', type=str,
+                        options=['adam'], tunable=False)
+
+        # if using 2 nodes with 4 gpus each the batch size here
+        #  (256) will be 256 / (2*8) = 16 per gpu
+        parser.opt_list('--batch_size', default=256 * 8, type=int,
+                        options=[32, 64, 128, 256], tunable=False,
+                        help='batch size will be divided over all gpus being used across all nodes')
         return parser

examples/new_project_templates/multi_node_cluster_template.py

@@ -0,0 +1,172 @@
+"""
+Multi-node example (GPU)
+"""
+import os
+import numpy as np
+from time import sleep
+import torch
+
+from test_tube import HyperOptArgumentParser, Experiment, SlurmCluster
+from pytorch_lightning.models.trainer import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main_local(hparams):
+    main(hparams, None, None)
+
+
+def main(hparams, cluster, results_dict):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    :return:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    print('loading model...')
+    model = LightningTemplateModel(hparams)
+    print('model built')
+
+    # ------------------------
+    # 2 INIT TEST TUBE EXP
+    # ------------------------
+    # when using grid search, it's possible for all models to start at once
+    # and use the same test tube experiment version
+    relative_node_id = int(os.environ['SLURM_NODEID'])
+    sleep(relative_node_id + 1)
+
+    # init experiment
+    exp = Experiment(
+        name=hyperparams.experiment_name,
+        save_dir=hyperparams.test_tube_save_path,
+        autosave=False,
+        description='test demo'
+    )
+
+    exp.argparse(hparams)
+    exp.save()
+
+    # ------------------------
+    # 3 DEFINE CALLBACKS
+    # ------------------------
+    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
+    early_stop = EarlyStopping(
+        monitor='val_acc',
+        patience=3,
+        verbose=True,
+        mode='max'
+    )
+
+    checkpoint = ModelCheckpoint(
+        filepath=model_save_path,
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
+    )
+
+    # ------------------------
+    # 4 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        experiment=exp,
+        cluster=cluster,
+        checkpoint_callback=checkpoint,
+        early_stop_callback=early_stop,
+        gpus=hparams.gpus,
+        nb_gpu_nodes=hyperparams.nb_gpu_nodes
+    )
+
+    # ------------------------
+    # 5 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+def optimize_on_cluster(hyperparams):
+    # enable cluster training
+    # log all scripts to the test tube folder
+    cluster = SlurmCluster(
+        hyperparam_optimizer=hyperparams,
+        log_path=hyperparams.slurm_log_path,
+    )
+
+    # email for cluster coms
+    cluster.notify_job_status(email='add_email_here', on_done=True, on_fail=True)
+
+    # configure cluster
+    cluster.per_experiment_nb_gpus = hyperparams.per_experiment_nb_gpus
+    cluster.per_experiment_nb_nodes = hyperparams.nb_gpu_nodes
+    cluster.job_time = '2:00:00'
+    cluster.gpu_type = 'volta'
+    cluster.memory_mb_per_node = 0
+
+    # any modules for code to run in env
+    cluster.add_command('source activate lightning')
+
+    # run only on 32GB voltas
+    cluster.add_slurm_cmd(cmd='constraint', value='volta32gb',
+                          comment='use 32gb gpus')
+    cluster.add_slurm_cmd(cmd='partition', value=hyperparams.gpu_partition,
+                          comment='use 32gb gpus')
+
+    # run hopt
+    # creates and submits jobs to slurm
+    cluster.optimize_parallel_cluster_gpu(
+        main,
+        nb_trials=hyperparams.nb_hopt_trials,
+        job_name=hyperparams.experiment_name
+    )
+
+
+if __name__ == '__main__':
+
+    # use default args
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    demo_log_dir = os.path.join(root_dir, 'pt_lightning_demo_logs')
+
+    checkpoint_dir = os.path.join(demo_log_dir, 'model_weights')
+    test_tube_dir = os.path.join(demo_log_dir, 'test_tube_data')
+    slurm_out_dir = os.path.join(demo_log_dir, 'slurm_scripts')
+
+    parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
+
+    # cluster args not defined inside the model
+    parent_parser.add_argument('--gpu_partition', type=str, help='consult your cluster manual')
+
+    # TODO: make 1 param
+    parent_parser.add_argument('--per_experiment_nb_gpus', type=int,
+                               help='how many gpus to use in a node')
+    parent_parser.add_argument('--gpus', type=str, default='-1',
+                               help='how many gpus to use in the node')
+
+    parent_parser.add_argument('--nb_gpu_nodes', type=int, default=1,
+                               help='how many nodes to use in a cluster')
+    parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+                               help='where to save logs')
+    parent_parser.add_argument('--slurm_log_path', type=str, default=slurm_out_dir,
+                               help='where to save slurm meta')
+    parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+                               help='where to save model')
+    parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+                               help='test tube exp name')
+    parent_parser.add_argument('--nb_hopt_trials', type=int, default=1,
+                               help='how many grid search trials to run')
+
+    # allow model to overwrite or extend args
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    # run on HPC cluster
+    print('RUNNING ON SLURM CLUSTER')
+    optimize_on_cluster(hyperparams)

examples/new_project_templates/single_cpu_template.py

@@ -0,0 +1,109 @@
+"""
+Runs a model on a single node on CPU only..
+"""
+import os
+import numpy as np
+import torch
+
+from test_tube import HyperOptArgumentParser, Experiment
+from pytorch_lightning.models.trainer import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    :return:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    print('loading model...')
+    model = LightningTemplateModel(hparams)
+    print('model built')
+
+    # ------------------------
+    # 2 INIT TEST TUBE EXP
+    # ------------------------
+
+    # init experiment
+    exp = Experiment(
+        name=hyperparams.experiment_name,
+        save_dir=hyperparams.test_tube_save_path,
+        autosave=False,
+        description='test demo'
+    )
+
+    exp.argparse(hparams)
+    exp.save()
+
+    # ------------------------
+    # 3 DEFINE CALLBACKS
+    # ------------------------
+    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
+    early_stop = EarlyStopping(
+        monitor='val_acc',
+        patience=3,
+        verbose=True,
+        mode='max'
+    )
+
+    checkpoint = ModelCheckpoint(
+        filepath=model_save_path,
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
+    )
+
+    # ------------------------
+    # 4 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        experiment=exp,
+        checkpoint_callback=checkpoint,
+        early_stop_callback=early_stop,
+    )
+
+    # ------------------------
+    # 5 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+
+    # dirs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    demo_log_dir = os.path.join(root_dir, 'pt_lightning_demo_logs')
+    checkpoint_dir = os.path.join(demo_log_dir, 'model_weights')
+    test_tube_dir = os.path.join(demo_log_dir, 'test_tube_data')
+
+    # although we user hyperOptParser, we are using it only as argparse right now
+    parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
+
+    # gpu args
+    parent_parser.add_argument('--test_tube_save_path', type=str,
+                               default=test_tube_dir, help='where to save logs')
+    parent_parser.add_argument('--model_save_path', type=str,
+                               default=checkpoint_dir, help='where to save model')
+    parent_parser.add_argument('--experiment_name', type=str,
+                               default='pt_lightning_exp_a', help='test tube exp name')
+
+    # allow model to overwrite or extend args
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    # run on HPC cluster
+    print('RUNNING ON CPU')
+    main(hyperparams)

examples/new_project_templates/single_gpu_node_16bit_template.py

@@ -0,0 +1,114 @@
+"""
+16-bit single node, CPU example
+"""
+import os
+import numpy as np
+import torch
+
+from test_tube import HyperOptArgumentParser, Experiment
+from pytorch_lightning.models.trainer import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    :return:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    print('loading model...')
+    model = LightningTemplateModel(hparams)
+    print('model built')
+
+    # ------------------------
+    # 2 INIT TEST TUBE EXP
+    # ------------------------
+
+    # init experiment
+    exp = Experiment(
+        name=hyperparams.experiment_name,
+        save_dir=hyperparams.test_tube_save_path,
+        autosave=False,
+        description='test demo'
+    )
+
+    exp.argparse(hparams)
+    exp.save()
+
+    # ------------------------
+    # 3 DEFINE CALLBACKS
+    # ------------------------
+    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
+    early_stop = EarlyStopping(
+        monitor='val_acc',
+        patience=3,
+        verbose=True,
+        mode='max'
+    )
+
+    checkpoint = ModelCheckpoint(
+        filepath=model_save_path,
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
+    )
+
+    # ------------------------
+    # 4 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        experiment=exp,
+        checkpoint_callback=checkpoint,
+        early_stop_callback=early_stop,
+        gpus=hparams.gpus,
+        use_amp=True
+    )
+
+    # ------------------------
+    # 5 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+
+    # dirs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    demo_log_dir = os.path.join(root_dir, 'pt_lightning_demo_logs')
+    checkpoint_dir = os.path.join(demo_log_dir, 'model_weights')
+    test_tube_dir = os.path.join(demo_log_dir, 'test_tube_data')
+
+    # although we user hyperOptParser, we are using it only as argparse right now
+    parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
+
+    # gpu args
+    parent_parser.add_argument('--gpus', type=str, default='-1',
+                               help='how many gpus to use in the node.'
+                                    'value -1 uses all the gpus on the node')
+    parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+                               help='where to save logs')
+    parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+                               help='where to save model')
+    parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+                               help='test tube exp name')
+
+    # allow model to overwrite or extend args
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    # run on HPC cluster
+    print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
+    main(hyperparams)

examples/new_project_templates/single_gpu_node_ddp_template.py

@@ -0,0 +1,114 @@
+"""
+Runs a model on a single node across N-gpus.
+"""
+import os
+import numpy as np
+import torch
+
+from test_tube import HyperOptArgumentParser, Experiment
+from pytorch_lightning.models.trainer import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    :return:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    print('loading model...')
+    model = LightningTemplateModel(hparams)
+    print('model built')
+
+    # ------------------------
+    # 2 INIT TEST TUBE EXP
+    # ------------------------
+
+    # init experiment
+    exp = Experiment(
+        name=hyperparams.experiment_name,
+        save_dir=hyperparams.test_tube_save_path,
+        autosave=False,
+        description='test demo'
+    )
+
+    exp.argparse(hparams)
+    exp.save()
+
+    # ------------------------
+    # 3 DEFINE CALLBACKS
+    # ------------------------
+    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
+    early_stop = EarlyStopping(
+        monitor='val_acc',
+        patience=3,
+        verbose=True,
+        mode='max'
+    )
+
+    checkpoint = ModelCheckpoint(
+        filepath=model_save_path,
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
+    )
+
+    # ------------------------
+    # 4 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        experiment=exp,
+        checkpoint_callback=checkpoint,
+        early_stop_callback=early_stop,
+        gpus=hparams.gpus,
+        distributed_backend='ddp'
+    )
+
+    # ------------------------
+    # 5 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+
+    # dirs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    demo_log_dir = os.path.join(root_dir, 'pt_lightning_demo_logs')
+    checkpoint_dir = os.path.join(demo_log_dir, 'model_weights')
+    test_tube_dir = os.path.join(demo_log_dir, 'test_tube_data')
+
+    # although we user hyperOptParser, we are using it only as argparse right now
+    parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
+
+    # gpu args
+    parent_parser.add_argument('--gpus', type=str, default='-1',
+                               help='how many gpus to use in the node.'
+                                    ' value -1 uses all the gpus on the node')
+    parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+                               help='where to save logs')
+    parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+                               help='where to save model')
+    parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+                               help='test tube exp name')
+
+    # allow model to overwrite or extend args
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    # run on HPC cluster
+    print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
+    main(hyperparams)

examples/new_project_templates/single_gpu_node_dp_template.py

@@ -0,0 +1,113 @@
+"""
+Runs a model on a single node across N-gpus using dataParallel
+"""
+import os
+import numpy as np
+import torch
+
+from test_tube import HyperOptArgumentParser, Experiment
+from pytorch_lightning.models.trainer import Trainer
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+def main(hparams):
+    """
+    Main training routine specific for this project
+    :param hparams:
+    :return:
+    """
+    # ------------------------
+    # 1 INIT LIGHTNING MODEL
+    # ------------------------
+    print('loading model...')
+    model = LightningTemplateModel(hparams)
+    print('model built')
+
+    # ------------------------
+    # 2 INIT TEST TUBE EXP
+    # ------------------------
+
+    # init experiment
+    exp = Experiment(
+        name=hyperparams.experiment_name,
+        save_dir=hyperparams.test_tube_save_path,
+        autosave=False,
+        description='test demo'
+    )
+
+    exp.argparse(hparams)
+    exp.save()
+
+    # ------------------------
+    # 3 DEFINE CALLBACKS
+    # ------------------------
+    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
+    early_stop = EarlyStopping(
+        monitor='val_acc',
+        patience=3,
+        verbose=True,
+        mode='max'
+    )
+
+    checkpoint = ModelCheckpoint(
+        filepath=model_save_path,
+        save_best_only=True,
+        verbose=True,
+        monitor='val_loss',
+        mode='min'
+    )
+
+    # ------------------------
+    # 4 INIT TRAINER
+    # ------------------------
+    trainer = Trainer(
+        experiment=exp,
+        checkpoint_callback=checkpoint,
+        early_stop_callback=early_stop,
+        gpus=hparams.gpus,
+    )
+
+    # ------------------------
+    # 5 START TRAINING
+    # ------------------------
+    trainer.fit(model)
+
+
+if __name__ == '__main__':
+
+    # dirs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    demo_log_dir = os.path.join(root_dir, 'pt_lightning_demo_logs')
+    checkpoint_dir = os.path.join(demo_log_dir, 'model_weights')
+    test_tube_dir = os.path.join(demo_log_dir, 'test_tube_data')
+
+    # although we user hyperOptParser, we are using it only as argparse right now
+    parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
+
+    # gpu args
+    parent_parser.add_argument('--gpus', type=str, default='-1',
+                               help='how many gpus to use in the node.'
+                                    ' value -1 uses all the gpus on the node')
+    parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+                               help='where to save logs')
+    parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+                               help='where to save model')
+    parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+                               help='test tube exp name')
+
+    # allow model to overwrite or extend args
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
+    hyperparams = parser.parse_args()
+
+    # ---------------------
+    # RUN TRAINING
+    # ---------------------
+    # run on HPC cluster
+    print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
+    main(hyperparams)

examples/new_project_templates/trainer_cpu_template.py

@@ -3,9 +3,10 @@ import sys
 
 from test_tube import HyperOptArgumentParser, Experiment
 from pytorch_lightning.models.trainer import Trainer
-from pytorch_lightning.utils.arg_parse import add_default_args
+from pytorch_lightning.utilities.arg_parse import add_default_args
 from pytorch_lightning.callbacks.pt_callbacks import EarlyStopping, ModelCheckpoint
-from docs.source.examples.example_model import ExampleModel
+
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
 
 
 def main(hparams):
@@ -28,7 +29,7 @@ def main(hparams):
     exp.save()
 
     # build model
-    model = ExampleModel(hparams)
+    model = LightningTemplateModel(hparams)
 
     # callbacks
     early_stop = EarlyStopping(
@@ -66,7 +67,7 @@ if __name__ == '__main__':
     add_default_args(parent_parser, root_dir)
 
     # allow model to overwrite or extend args
-    parser = ExampleModel.add_model_specific_args(parent_parser)
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser)
     hyperparams = parser.parse_args()
 
     # train model

examples/new_project_templates/trainer_gpu_cluster_template.py

@@ -1,208 +0,0 @@
-import os
-import sys
-import numpy as np
-from time import sleep
-import torch
-
-from test_tube import HyperOptArgumentParser, Experiment, SlurmCluster
-from pytorch_lightning.models.trainer import Trainer
-from pytorch_lightning.utils.arg_parse import add_default_args
-
-from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
-
-SEED = 2334
-torch.manual_seed(SEED)
-np.random.seed(SEED)
-
-# ---------------------
-# DEFINE MODEL HERE
-# ---------------------
-from lightning_module_template import LightningTemplateModel
-# ---------------------
-
-AVAILABLE_MODELS = {
-    'model_template': LightningTemplateModel
-}
-
-
-"""
-Allows training by using command line arguments
-Run by:
-# TYPE YOUR RUN COMMAND HERE
-"""
-
-
-def main_local(hparams):
-    main(hparams, None, None)
-
-
-def main(hparams, cluster, results_dict):
-    """
-    Main training routine specific for this project
-    :param hparams:
-    :return:
-    """
-    on_gpu = hparams.gpus is not None and torch.cuda.is_available()
-
-    device = 'cuda' if on_gpu else 'cpu'
-    hparams.__setattr__('device', device)
-    hparams.__setattr__('on_gpu', on_gpu)
-    hparams.__setattr__('nb_gpus', torch.cuda.device_count())
-    hparams.__setattr__('inference_mode', hparams.model_load_weights_path is not None)
-
-    # delay each training start to not overwrite logs
-    process_position, current_gpu = TRAINING_MODEL.get_process_position(hparams.gpus)
-    sleep(process_position + 1)
-
-    # init experiment
-    log_dir = os.path.dirname(os.path.realpath(__file__))
-    log_dir = os.path.join(log_dir, 'test_tube_demo_logs')
-    exp = Experiment(
-        name='test_tube_exp',
-        save_dir=log_dir,
-        autosave=False,
-        description='test demo'
-    )
-
-    exp.argparse(hparams)
-    exp.save()
-
-    # build model
-    print('loading model...')
-    model = TRAINING_MODEL(hparams)
-    print('model built')
-
-    # callbacks
-    early_stop = EarlyStopping(
-        monitor=hparams.early_stop_metric,
-        patience=hparams.early_stop_patience,
-        verbose=True,
-        mode=hparams.early_stop_mode
-    )
-
-    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
-    checkpoint = ModelCheckpoint(
-        filepath=model_save_path,
-        save_best_only=True,
-        verbose=True,
-        monitor=hparams.model_save_monitor_value,
-        mode=hparams.model_save_monitor_mode
-    )
-
-    # gpus are ; separated for inside a node and , within nodes
-    gpu_list = None
-    if hparams.gpus is not None:
-        gpu_list = [int(x) for x in hparams.gpus.split(';')]
-
-    # configure trainer
-    trainer = Trainer(
-        experiment=exp,
-        cluster=cluster,
-        checkpoint_callback=checkpoint,
-        early_stop_callback=early_stop,
-        gpus=gpu_list,
-    )
-
-    # train model
-    trainer.fit(model)
-
-
-def get_default_parser(strategy, root_dir):
-
-    possible_model_names = list(AVAILABLE_MODELS.keys())
-    parser = HyperOptArgumentParser(strategy=strategy, add_help=False)
-    add_default_args(parser, root_dir, possible_model_names=possible_model_names, rand_seed=SEED)
-    return parser
-
-
-def get_model_name(args):
-    for i, arg in enumerate(args):
-        if 'model_name' in arg:
-            return args[i+1]
-
-
-def optimize_on_cluster(hyperparams):
-    # enable cluster training
-    cluster = SlurmCluster(
-        hyperparam_optimizer=hyperparams,
-        log_path=hyperparams.tt_save_path,
-        test_tube_exp_name=hyperparams.tt_name
-    )
-
-    # email for cluster coms
-    cluster.notify_job_status(email='add_email_here', on_done=True, on_fail=True)
-
-    # configure cluster
-    cluster.per_experiment_nb_gpus = hyperparams.per_experiment_nb_gpus
-    cluster.job_time = '48:00:00'
-    cluster.gpu_type = '1080ti'
-    cluster.memory_mb_per_node = 48000
-
-    # any modules for code to run in env
-    cluster.add_command('source activate pytorch_lightning')
-
-    # name of exp
-    job_display_name = hyperparams.tt_name.split('_')[0]
-    job_display_name = job_display_name[0:3]
-
-    # run hopt
-    print('submitting jobs...')
-    cluster.optimize_parallel_cluster_gpu(
-        main,
-        nb_trials=hyperparams.nb_hopt_trials,
-        job_name=job_display_name
-    )
-
-
-if __name__ == '__main__':
-
-    model_name = get_model_name(sys.argv)
-    if model_name is None:
-        model_name = 'model_template'
-
-    # use default args
-    root_dir = os.path.dirname(os.path.realpath(__file__))
-    parent_parser = get_default_parser(strategy='random_search', root_dir=root_dir)
-
-    # allow model to overwrite or extend args
-    TRAINING_MODEL = AVAILABLE_MODELS[model_name]
-    parser = TRAINING_MODEL.add_model_specific_args(parent_parser, root_dir)
-    hyperparams = parser.parse_args()
-
-    # format GPU layout
-    os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
-
-    # ---------------------
-    # RUN TRAINING
-    # ---------------------
-
-    # cluster and CPU
-    if hyperparams.on_cluster:
-        # run on HPC cluster
-        print('RUNNING ON SLURM CLUSTER')
-        gpu_ids = hyperparams.gpus.split(';')
-        os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
-        optimize_on_cluster(hyperparams)
-
-    elif hyperparams.gpus is None:
-        # run on cpu
-        print('RUNNING ON CPU')
-        main(hyperparams, None, None)
-
-    # single or multiple GPUs on same machine
-    gpu_ids = hyperparams.gpus.split(';')
-    if hyperparams.interactive:
-        # run on 1 gpu
-        print(f'RUNNING INTERACTIVE MODE ON GPUS. gpu ids: {gpu_ids}')
-        os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
-        main(hyperparams, None, None)
-
-    else:
-        # multiple GPUs on same machine
-        print(f'RUNNING MULTI GPU. GPU ids: {gpu_ids}')
-        hyperparams.optimize_parallel_gpu(
-            main_local,
-            gpu_ids=gpu_ids,
-            nb_trials=hyperparams.nb_hopt_trials,
-            nb_workers=len(gpu_ids)
-        )

mkdocs.yml

@@ -1,10 +1,10 @@
-site_name: Pytorch lightning Documentation
+site_name: PyTorch lightning Documentation
 theme:
   name: 'material'
 docs_dir: docs
 repo_url: https://github.com/williamFalcon/pytorch-lightning
 site_dir: 'site'
-site_description: 'Documentation for Pytorch LightningModule, the researcher version of keras.'
+site_description: 'Documentation for PyTorch LightningModule, the researcher version of keras.'
 
 dev_addr: '0.0.0.0:8000'
 #google_analytics: ['UA-aasd', 'sitename']

pytorch_lightning/__init__.py

@@ -1 +1,9 @@
-from .models import Trainer
+from .models.trainer import Trainer
+from .root_module.root_module import LightningModule
+from .root_module.decorators import data_loader
+
+__all__ = [
+    'Trainer',
+    'LightningModule',
+    'data_loader',
+]

pytorch_lightning/callbacks/__init__.py

@@ -1 +1,6 @@
-from .pt_callbacks import EarlyStopping, ModelCheckpoint
+from .pt_callbacks import EarlyStopping, ModelCheckpoint
+
+__all__ = [
+    'EarlyStopping',
+    'ModelCheckpoint',
+]

pytorch_lightning/callbacks/pt_callbacks.py

@@ -1,6 +1,9 @@
+import os
+import shutil
+
 import numpy as np
-import os, shutil
-from pytorch_lightning.pt_overrides.override_data_parallel import LightningDataParallel
+
+from pytorch_lightning.pt_overrides.override_data_parallel import LightningDistributedDataParallel
 
 
 class Callback(object):
@@ -34,7 +37,7 @@ class Callback(object):
         self.params = params
 
     def set_model(self, model):
-        if type(model) is LightningDataParallel:
+        if type(model) is LightningDistributedDataParallel:
             model = model.module
         self.model = model
 
@@ -119,9 +122,9 @@ class EarlyStopping(Callback):
         current = logs.get(self.monitor)
         stop_training = False
         if current is None:
-            print('Early stopping conditioned on metric `%s` ''which is not available. Available metrics are: %s' %
-                (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning
-            )
+            print('Early stopping conditioned on metric `%s` '
+                  'which is not available. Available metrics are: %s' %
+                  (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning)
             exit(-1)
 
         if self.monitor_op(current - self.min_delta, self.best):
@@ -185,8 +188,7 @@ class ModelCheckpoint(Callback):
 
         if mode not in ['auto', 'min', 'max']:
             print('ModelCheckpoint mode %s is unknown, '
-                          'fallback to auto mode.' % (mode),
-                          RuntimeWarning)
+                  'fallback to auto mode.' % (mode), RuntimeWarning)
             mode = 'auto'
 
         if mode == 'min':
@@ -230,8 +232,8 @@ class ModelCheckpoint(Callback):
             if self.save_best_only:
                 current = logs.get(self.monitor)
                 if current is None:
-                    print('Can save best model only with %s available, '
-                                  'skipping.' % (self.monitor), RuntimeWarning)
+                    print('Can save best model only with %s available,'
+                          ' skipping.' % (self.monitor), RuntimeWarning)
                 else:
                     if self.monitor_op(current, self.best):
                         if self.verbose > 0:
@@ -260,4 +262,3 @@ if __name__ == '__main__':
         print(loss)
         if should_stop:
             break
-

pytorch_lightning/models/__init__.py

@@ -1 +0,0 @@
-from .trainer import Trainer

pytorch_lightning/models/sample_model_template/model_template.py

@@ -1,203 +0,0 @@
-import torch.nn as nn
-import numpy as np
-from pytorch_lightning.root_module.root_module import LightningModule
-from test_tube import HyperOptArgumentParser
-from torchvision.datasets import MNIST
-import torchvision.transforms as transforms
-import torch
-import torch.nn.functional as F
-
-
-class ExampleModel1(LightningModule):
-    """
-    Sample model to show how to define a template
-    """
-
-    def __init__(self, hparams):
-        # init superclass
-        super(ExampleModel1, self).__init__(hparams)
-
-        self.batch_size = hparams.batch_size
-
-        # build model
-        self.__build_model()
-
-    # ---------------------
-    # MODEL SETUP
-    # ---------------------
-    def __build_model(self):
-        """
-        Layout model
-        :return:
-        """
-        self.c_d1 = nn.Linear(in_features=self.hparams.in_features, out_features=self.hparams.hidden_dim)
-        self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
-        self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
-
-        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim, out_features=self.hparams.out_features)
-
-    # ---------------------
-    # TRAINING
-    # ---------------------
-    def forward(self, x):
-        x = self.c_d1(x)
-        x = F.tanh(x)
-        x = self.c_d1_bn(x)
-        x = self.c_d1_drop(x)
-
-        x = self.c_d2(x)
-        logits = F.log_softmax(x, dim=1)
-
-        return logits
-
-    def loss(self, labels, logits):
-        nll = F.nll_loss(logits, labels)
-        return nll
-
-    def training_step(self, data_batch):
-        """
-        Called inside the training loop
-        :param data_batch:
-        :return:
-        """
-        # forward pass
-        x, y = data_batch
-        x = x.view(x.size(0), -1)
-        y_hat = self.forward(x)
-
-        # calculate loss
-        loss_val = self.loss(y, y_hat)
-
-        tqdm_dic = {'jefe': 1}
-        return loss_val, tqdm_dic
-
-    def validation_step(self, data_batch):
-        """
-        Called inside the validation loop
-        :param data_batch:
-        :return:
-        """
-        x, y = data_batch
-        x = x.view(x.size(0), -1)
-        y_hat = self.forward(x)
-
-        loss_val = self.loss(y, y_hat)
-
-        # acc
-        labels_hat = torch.argmax(y_hat, dim=1)
-        val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
-
-        output = {'y_hat': y_hat, 'val_loss': loss_val.item(), 'val_acc': val_acc}
-        return output
-
-    def validation_end(self, outputs):
-        """
-        Called at the end of validation to aggregate outputs
-        :param outputs: list of individual outputs of each validation step
-        :return:
-        """
-        val_loss_mean = 0
-        accs = []
-        for output in outputs:
-            val_loss_mean += output['val_loss']
-            accs.append(output['val_acc'])
-
-        val_loss_mean /= len(outputs)
-        tqdm_dic = {'val_loss': val_loss_mean, 'val_acc': np.mean(accs)}
-        return tqdm_dic
-
-    def update_tng_log_metrics(self, logs):
-        return logs
-
-    # ---------------------
-    # MODEL SAVING
-    # ---------------------
-    def get_save_dict(self):
-        checkpoint = {
-            'state_dict': self.state_dict(),
-        }
-
-        return checkpoint
-
-    def load_model_specific(self, checkpoint):
-        self.load_state_dict(checkpoint['state_dict'])
-        pass
-
-    # ---------------------
-    # TRAINING SETUP
-    # ---------------------
-    def configure_optimizers(self):
-        """
-        return whatever optimizers we want here
-        :return: list of optimizers
-        """
-        optimizer = self.choose_optimizer(self.hparams.optimizer_name, self.parameters(), {'lr': self.hparams.learning_rate}, 'optimizer')
-        self.optimizers = [optimizer]
-        return self.optimizers
-
-    def __dataloader(self, train):
-        # init data generators
-        transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
-
-        dataset = MNIST(root=self.hparams.data_root, train=train, transform=transform, download=True)
-
-        loader = torch.utils.data.DataLoader(
-            dataset=dataset,
-            batch_size=self.hparams.batch_size,
-            shuffle=True
-        )
-
-        return loader
-
-    @property
-    def tng_dataloader(self):
-        if self._tng_dataloader is None:
-            try:
-                self._tng_dataloader = self.__dataloader(train=True)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._tng_dataloader
-
-    @property
-    def val_dataloader(self):
-        if self._val_dataloader is None:
-            try:
-                self._val_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._val_dataloader
-
-    @property
-    def test_dataloader(self):
-        if self._test_dataloader is None:
-            try:
-                self._test_dataloader = self.__dataloader(train=False)
-            except Exception as e:
-                print(e)
-                raise e
-        return self._test_dataloader
-
-    @staticmethod
-    def add_model_specific_args(parent_parser):
-        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
-
-        # param overwrites
-        # parser.set_defaults(gradient_clip=5.0)
-
-        # network params
-        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
-        parser.add_argument('--in_features', default=28*28)
-        parser.add_argument('--hidden_dim', default=500)
-        parser.add_argument('--out_features', default=10)
-
-        # data
-        parser.add_argument('--data_root', default='/Users/williamfalcon/Developer/personal/research_lib/research_proj/datasets/mnist', type=str)
-
-        # training params (opt)
-        parser.opt_list('--learning_rate', default=0.001, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
-                        tunable=False)
-        parser.opt_list('--batch_size', default=256, type=int, options=[32, 64, 128, 256], tunable=False)
-        parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
-        return parser

pytorch_lightning/pt_overrides/override_data_parallel.py

@@ -1,12 +1,27 @@
 from torch.nn import DataParallel
+from torch.nn.parallel import DistributedDataParallel
+import itertools
+from itertools import chain
 
 import threading
 import torch
 from torch.cuda._utils import _get_device_index
-import pdb
 
 
-def get_a_var(obj):
+def _find_tensors(obj):  # pragma: no cover
+    r"""
+    Recursively find all tensors contained in the specified object.
+    """
+    if isinstance(obj, torch.Tensor):
+        return [obj]
+    if isinstance(obj, (list, tuple)):
+        return itertools.chain(*map(_find_tensors, obj))
+    if isinstance(obj, dict):
+        return itertools.chain(*map(_find_tensors, obj.values()))
+    return []
+
+
+def get_a_var(obj):  # pragma: no cover
     if isinstance(obj, torch.Tensor):
         return obj
 
@@ -26,11 +41,76 @@ class LightningDataParallel(DataParallel):
     Override the forward call in lightning so it goes to training and validation step respectively
     """
 
+    def forward(self, *inputs, **kwargs):
+        if not self.device_ids:
+            return self.module(*inputs, **kwargs)
+
+        for t in chain(self.module.parameters(), self.module.buffers()):
+            if t.device != self.src_device_obj:
+                raise RuntimeError("module must have its parameters and buffers "
+                                   "on device {} (device_ids[0]) but found one of "
+                                   "them on device: {}".format(self.src_device_obj, t.device))
+
+        inputs, kwargs = self.scatter(inputs, kwargs, self.device_ids)
+        if len(self.device_ids) == 1:
+            # lightning
+            if self.module.training:
+                return self.module.training_step(*inputs[0], **kwargs[0])
+            else:
+                return self.module.validation_step(*inputs[0], **kwargs[0])
+
+        replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
+        outputs = self.parallel_apply(replicas, inputs, kwargs)
+        return self.gather(outputs, self.output_device)
+
     def parallel_apply(self, replicas, inputs, kwargs):
         return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
 
 
-def parallel_apply(modules, inputs, kwargs_tup=None, devices=None):
+class LightningDistributedDataParallel(DistributedDataParallel):
+    """
+    Override the forward call in lightning so it goes to training and validation step respectively
+    """
+
+    def parallel_apply(self, replicas, inputs, kwargs):
+        return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
+
+    def forward(self, *inputs, **kwargs):  # pragma: no cover
+        self._sync_params()
+        if self.device_ids:
+            inputs, kwargs = self.scatter(inputs, kwargs, self.device_ids)
+            if len(self.device_ids) == 1:
+                # --------------
+                # LIGHTNING MOD
+                # --------------
+                # normal
+                # output = self.module(*inputs[0], **kwargs[0])
+
+                # lightning
+                if self.module.training:
+                    output = self.module.training_step(*inputs[0], **kwargs[0])
+                else:
+                    output = self.module.validation_step(*inputs[0], **kwargs[0])
+            else:
+                outputs = self.parallel_apply(self._module_copies[:len(inputs)], inputs, kwargs)
+                output = self.gather(outputs, self.output_device)
+        else:
+            output = self.module(*inputs, **kwargs)
+
+        if torch.is_grad_enabled():
+            # We'll return the output object verbatim since it is a freeform
+            # object. We need to find any tensors in this object, though,
+            # because we need to figure out which parameters were used during
+            # this forward pass, to ensure we short circuit reduction for any
+            # unused parameters. Only if `find_unused_parameters` is set.
+            if self.find_unused_parameters:
+                self.reducer.prepare_for_backward(list(_find_tensors(output)))
+            else:
+                self.reducer.prepare_for_backward([])
+        return output
+
+
+def parallel_apply(modules, inputs, kwargs_tup=None, devices=None):  # pragma: no cover
     r"""Applies each `module` in :attr:`modules` in parallel on arguments
     contained in :attr:`inputs` (positional) and :attr:`kwargs_tup` (keyword)
     on each of :attr:`devices`.
@@ -102,4 +182,4 @@ def parallel_apply(modules, inputs, kwargs_tup=None, devices=None):
         if isinstance(output, Exception):
             raise output
         outputs.append(output)
-    return outputs
+    return outputs

pytorch_lightning/root_module/decorators.py

@@ -0,0 +1,17 @@
+
+def data_loader(fn):
+    """
+    Decorator to make any fx with this use the lazy property
+    :param fn:
+    :return:
+    """
+
+    attr_name = '_lazy_' + fn.__name__
+
+    @property
+    def _data_loader(self):
+        if not hasattr(self, attr_name):
+            setattr(self, attr_name, fn(self))
+        return getattr(self, attr_name)
+
+    return _data_loader

pytorch_lightning/root_module/grads.py

@@ -1,10 +1,9 @@
-import numpy as np
-from torch import nn
-
 """
 Module to describe gradients
 """
 
+from torch import nn
+
 
 class GradInformation(nn.Module):
 
@@ -18,23 +17,13 @@ class GradInformation(nn.Module):
                     total_norm += param_norm ** norm_type
                     norm = param_norm ** (1 / norm_type)
 
-                    results['grad_{}_norm_{}'.format(norm_type, i)] = round(norm.data.cpu().numpy().flatten()[0], 3)
-                except Exception as e:
+                    grad = round(norm.data.cpu().numpy().flatten()[0], 3)
+                    results['grad_{}_norm_{}'.format(norm_type, i)] = grad
+                except Exception:
                     # this param had no grad
                     pass
 
         total_norm = total_norm ** (1. / norm_type)
-        results['grad_{}_norm_total'.format(norm_type)] = round(total_norm.data.cpu().numpy().flatten()[0], 3)
+        grad = round(total_norm.data.cpu().numpy().flatten()[0], 3)
+        results['grad_{}_norm_total'.format(norm_type)] = grad
         return results
-
-
-    def describe_grads(self):
-        for p in self.parameters():
-            g = p.grad.data.numpy().flatten()
-            print(np.max(g), np.min(g), np.mean(g))
-
-
-    def describe_params(self):
-        for p in self.parameters():
-            g = p.data.numpy().flatten()
-            print(np.max(g), np.min(g), np.mean(g))

pytorch_lightning/root_module/hooks.py

@@ -1,6 +1,15 @@
 import torch
 
+
 class ModelHooks(torch.nn.Module):
+
+    def on_sanity_check_start(self):
+        """
+        Called before starting validate
+        :return:
+        """
+        pass
+
     def on_batch_start(self, data_batch):
         pass
 
@@ -19,3 +28,26 @@ class ModelHooks(torch.nn.Module):
     def on_post_performance_check(self):
         pass
 
+    def on_tng_metrics(self, metrics):
+        pass
+
+    def on_before_zero_grad(self, optimizer):
+        """
+        Called after optimizer.step() and before optimizer.zero_grad()
+
+        for optimizer in optimizers:
+            optimizer.step()
+            model.on_before_zero_grad(optimizer) # < ---- called here
+            optimizer.zero_grad
+
+        :param optimizer:
+        :return:
+        """
+        pass
+
+    def on_after_backward(self):
+        """
+        Called after loss.backward() and before optimizers do anything
+        :return:
+        """
+        pass

pytorch_lightning/root_module/memory.py

@@ -1,14 +1,14 @@
-import torch
-import gc
-import subprocess
-import numpy as np
-import pandas as pd
-
-
 '''
 Generates a summary of a model's layers and dimensionality
 '''
 
+import gc
+
+import torch
+import subprocess
+import numpy as np
+import pandas as pd
+
 
 class ModelSummary(object):
 
@@ -33,33 +33,42 @@ class ModelSummary(object):
         mods = list(self.model.modules())
         in_sizes = []
         out_sizes = []
-        input_ = self.example_input_array
-        for i in range(1, len(mods)):
-            m = mods[i]
-            if type(input_) is list or type(input_) is tuple:
-                out = m(*input_)
-            else:
-                out = m(input_)
+        input_ = self.model.example_input_array
 
-            if type(input_) is tuple or type(input_) is list:
-                in_size = []
-                for x in input_:
-                    if type(x) is list:
-                        in_size.append(len(x))
-                    else:
-                        in_size.append(x.size())
-            else:
-                in_size = np.array(input_.size())
+        if self.model.on_gpu:
+            input_ = input_.cuda(0)
 
-            in_sizes.append(in_size)
+        if self.model.trainer.use_amp:
+            input_ = input_.half()
 
-            if type(out) is tuple or type(out) is list:
-                out_size = np.asarray([x.size() for x in out])
-            else:
-                out_size = np.array(out.size())
+        with torch.no_grad():
 
-            out_sizes.append(out_size)
-            input_ = out
+            for i in range(1, len(mods)):
+                m = mods[i]
+                if type(input_) is list or type(input_) is tuple:  # pragma: no cover
+                    out = m(*input_)
+                else:
+                    out = m(input_)
+
+                if type(input_) is tuple or type(input_) is list:  # pragma: no cover
+                    in_size = []
+                    for x in input_:
+                        if type(x) is list:
+                            in_size.append(len(x))
+                        else:
+                            in_size.append(x.size())
+                else:
+                    in_size = np.array(input_.size())
+
+                in_sizes.append(in_size)
+
+                if type(out) is tuple or type(out) is list:  # pragma: no cover
+                    out_size = np.asarray([x.size() for x in out])
+                else:
+                    out_size = np.array(out.size())
+
+                out_sizes.append(out_size)
+                input_ = out
 
         self.in_sizes = in_sizes
         self.out_sizes = out_sizes
@@ -85,7 +94,7 @@ class ModelSummary(object):
         mods = list(self.model.modules())
         sizes = []
 
-        for i in range(1,len(mods)):
+        for i in range(1, len(mods)):
             m = mods[i]
             p = list(m.parameters())
             modsz = []
@@ -114,13 +123,22 @@ class ModelSummary(object):
         Layer Name, Layer Type, Input Size, Output Size, Number of Parameters
         '''
 
-        df = pd.DataFrame( np.zeros( (len(self.layer_names), 3) ) )
-        df.columns = ['Name', 'Type', 'Params']
+        cols = ['Name', 'Type', 'Params']
+        if self.model.example_input_array is not None:
+            cols.extend(['In_sizes', 'Out_sizes'])
+
+        df = pd.DataFrame(np.zeros((len(self.layer_names), len(cols))))
+        df.columns = cols
 
         df['Name'] = self.layer_names
         df['Type'] = self.layer_types
         df['Params'] = self.param_nums
 
+        if self.model.example_input_array is not None:
+
+            df['In_sizes'] = self.in_sizes
+            df['Out_sizes'] = self.out_sizes
+
         self.summary = df
         return
 
@@ -128,19 +146,22 @@ class ModelSummary(object):
         self.get_layer_names()
         self.get_parameter_sizes()
         self.get_parameter_nums()
+
+        if self.model.example_input_array is not None:
+            self.get_variable_sizes()
         self.make_summary()
 
 
-def print_mem_stack():
+def print_mem_stack():  # pragma: no cover
     for obj in gc.get_objects():
         try:
             if torch.is_tensor(obj) or (hasattr(obj, 'data') and torch.is_tensor(obj.data)):
                 print(type(obj), obj.size())
-        except Exception as e:
+        except Exception:
             pass
 
 
-def count_mem_items():
+def count_mem_items():  # pragma: no cover
     nb_params = 0
     nb_tensors = 0
     for obj in gc.get_objects():
@@ -151,7 +172,7 @@ def count_mem_items():
                     nb_params += 1
                 else:
                     nb_tensors += 1
-        except Exception as e:
+        except Exception:
             pass
 
     return nb_params, nb_tensors
@@ -175,6 +196,6 @@ def get_gpu_memory_map():
     gpu_memory = [int(x) for x in result.strip().split('\n')]
     gpu_memory_map = {}
     for k, v in zip(range(len(gpu_memory)), gpu_memory):
-        k = f'gpu_{k}'
+        k = 'gpu_%i' % k
         gpu_memory_map[k] = v
     return gpu_memory_map

pytorch_lightning/root_module/model_saving.py

@@ -1,29 +1,56 @@
-import torch
 import os
 import re
-import pdb
-from pytorch_lightning.pt_overrides.override_data_parallel import LightningDataParallel
+
+import torch
+
+from pytorch_lightning.pt_overrides.override_data_parallel import (
+    LightningDistributedDataParallel, LightningDataParallel)
+
 
 class ModelIO(object):
 
-    def load_model_specific(self, checkpoint):
+    def on_load_checkpoint(self, checkpoint):
         """
         Do something with the checkpoint
+        Gives model a chance to load something before state_dict is restored
         :param checkpoint:
         :return:
         """
-        raise NotImplementedError
+        pass
 
-    def get_save_dict(self):
+    def on_save_checkpoint(self, checkpoint):
         """
-        Return specific things for the model
+        Give the model a chance to add something to the checkpoint.
+        state_dict is already there
+        """
+        pass
+
+    # -------------------------
+    # OPTIONAL HOOKS
+    # -------------------------
+    def on_hpc_save(self, checkpoint):
+        """
+        Hook to do whatever you need right before Slurm manager saves the model
         :return:
         """
-        raise NotImplementedError
+        pass
+
+    def on_hpc_load(self, checkpoint):
+        """
+        Hook to do whatever you need right before Slurm manager loads the model
+        :return:
+        """
+        pass
 
 
 class TrainerIO(object):
 
+    def __get_model(self):
+        is_dp_module = isinstance(self.model, (LightningDistributedDataParallel,
+                                               LightningDataParallel))
+        model = self.model.module if is_dp_module else self.model
+        return model
+
     # --------------------
     # MODEL SAVE CHECKPOINT
     # --------------------
@@ -33,27 +60,57 @@ class TrainerIO(object):
         # do the actual save
         torch.save(checkpoint, filepath)
 
+    def restore(self, checkpoint_path, on_gpu):
+
+        if on_gpu:
+            checkpoint = torch.load(checkpoint_path)
+        else:
+            checkpoint = torch.load(checkpoint_path, map_location=lambda storage, loc: storage)
+
+        # load training state (affects trainer only)
+        self.restore_training_state(checkpoint)
+
+        # load model state
+        model = self.__get_model()
+
+        # load the state_dict on the model automatically
+        model.load_state_dict(checkpoint['state_dict'])
+
     def dump_checkpoint(self):
+
         checkpoint = {
             'epoch': self.current_epoch,
-            'checkpoint_callback_best': self.checkpoint_callback.best,
-            'early_stop_callback_wait': self.early_stop_callback.wait,
-            'early_stop_callback_patience': self.early_stop_callback.patience,
             'global_step': self.global_step
         }
 
+        if self.checkpoint_callback is not None:
+            checkpoint['checkpoint_callback_best'] = self.checkpoint_callback.best
+
+        if self.early_stop_callback is not None:
+            checkpoint['early_stop_callback_wait'] = self.early_stop_callback.wait
+            checkpoint['early_stop_callback_patience'] = self.early_stop_callback.patience
+
+        # save optimizers
         optimizer_states = []
         for i, optimizer in enumerate(self.optimizers):
             optimizer_states.append(optimizer.state_dict())
 
         checkpoint['optimizer_states'] = optimizer_states
 
-        # request what to save from the model
-        model = self.model.module if type(self.model) is LightningDataParallel else self.model
-        checkpoint_dict = model.get_save_dict()
+        # save lr schedulers
+        lr_schedulers = []
+        for i, scheduler in enumerate(self.lr_schedulers):
+            lr_schedulers.append(scheduler.state_dict())
+
+        checkpoint['lr_schedulers'] = lr_schedulers
+
+        # add the state_dict from the model
+        model = self.__get_model()
+        checkpoint['state_dict'] = model.state_dict()
+
+        # give the model a chance to add a few things
+        model.on_save_checkpoint(checkpoint)
 
-        # merge trainer and model saving items
-        checkpoint.update(checkpoint_dict)
         return checkpoint
 
     # --------------------
@@ -64,13 +121,16 @@ class TrainerIO(object):
             return
 
         # allow test tube to handle model check pointing automatically
-        self.cluster.set_checkpoint_save_function(
-            self.hpc_save,
-            kwargs={
-                'folderpath': self.checkpoint_callback.filepath,
-                'experiment': self.experiment
-            }
-        )
+        # only if proc 0 so we don't trigger world_size resubmits
+        if self.proc_rank == 0:
+            self.cluster.set_checkpoint_save_function(
+                self.hpc_save,
+                kwargs={
+                    'folderpath': self.checkpoint_callback.filepath,
+                    'experiment': self.experiment
+                }
+            )
+
         self.cluster.set_checkpoint_load_function(
             self.hpc_load,
             kwargs={
@@ -86,9 +146,13 @@ class TrainerIO(object):
         :param checkpoint:
         :return:
         """
-        self.checkpoint_callback.best = checkpoint['checkpoint_callback_best']
-        self.early_stop_callback.wait = checkpoint['early_stop_callback_wait']
-        self.early_stop_callback.patience = checkpoint['early_stop_callback_patience']
+        if self.checkpoint_callback is not None:
+            self.checkpoint_callback.best = checkpoint['checkpoint_callback_best']
+
+        if self.early_stop_callback is not None:
+            self.early_stop_callback.wait = checkpoint['early_stop_callback_wait']
+            self.early_stop_callback.patience = checkpoint['early_stop_callback_patience']
+
         self.global_step = checkpoint['global_step']
         self.current_epoch = checkpoint['epoch']
 
@@ -97,6 +161,11 @@ class TrainerIO(object):
         for optimizer, opt_state in zip(self.optimizers, optimizer_states):
             optimizer.load_state_dict(opt_state)
 
+        # restore the lr schedulers
+        lr_schedulers = checkpoint['lr_schedulers']
+        for scheduler, lrs_state in zip(self.lr_schedulers, lr_schedulers):
+            scheduler.load_state_dict(lrs_state)
+
     # ----------------------------------
     # PRIVATE OPS
     # ----------------------------------
@@ -116,11 +185,16 @@ class TrainerIO(object):
             os.makedirs(folderpath, exist_ok=True)
         filepath = '{}/hpc_ckpt_{}.ckpt'.format(folderpath, ckpt_number)
 
-        # request what to save from the model
-        checkpoint_dict = self.dump_checkpoint()
+        # give model a chance to do something on hpc_save
+        model = self.__get_model()
+        checkpoint = self.dump_checkpoint()
+
+        model.on_hpc_save(checkpoint)
 
         # do the actual save
-        torch.save(checkpoint_dict, filepath)
+        torch.save(checkpoint, filepath)
+
+        return filepath
 
     def hpc_load(self, folderpath, on_gpu):
         filepath = '{}/hpc_ckpt_{}.ckpt'.format(folderpath, self.max_ckpt_in_folder(folderpath))
@@ -130,22 +204,27 @@ class TrainerIO(object):
         else:
             checkpoint = torch.load(filepath, map_location=lambda storage, loc: storage)
 
-        # load training state
+        # load training state (affects trainer only)
         self.restore_training_state(checkpoint)
 
         # load model state
-        model = self.model.module if type(self.model) is LightningDataParallel else self.model
-        model.load_model_specific(checkpoint)
+        model = self.__get_model()
 
-    def max_ckpt_in_folder(self, path):
+        # load the state_dict on the model automatically
+        model.load_state_dict(checkpoint['state_dict'])
+
+        # call model hook
+        model.on_hpc_load(checkpoint)
+
+    def max_ckpt_in_folder(self, path, name_key='ckpt_'):
         files = os.listdir(path)
-        files = [x for x in files if 'ckpt_' in x]
+        files = [x for x in files if name_key in x]
         if len(files) == 0:
             return 0
 
         ckpt_vs = []
         for name in files:
-            name = name.split('ckpt_')[-1]
+            name = name.split(name_key)[-1]
             name = re.sub('[^0-9]', '', name)
             ckpt_vs.append(int(name))
 

pytorch_lightning/root_module/optimization.py

@@ -1,22 +0,0 @@
-from torch import nn
-from torch import optim
-
-
-class OptimizerConfig(nn.Module):
-
-    def choose_optimizer(self, optimizer, params, optimizer_params, opt_name_key):
-        if optimizer == 'adam':
-            optimizer = optim.Adam(params, **optimizer_params)
-        if optimizer == 'sparse_adam':
-            optimizer = optim.SparseAdam(params, **optimizer_params)
-        if optimizer == 'sgd':
-            optimizer = optim.SGD(params, **optimizer_params)
-        if optimizer == 'adadelta':
-            optimizer = optim.Adadelta(params, **optimizer_params)
-
-        # transfer opt state if loaded
-        if opt_name_key in self.loaded_optimizer_states_dict:
-            state = self.loaded_optimizer_states_dict[opt_name_key]
-            optimizer.load_state_dict(state)
-
-        return optimizer

pytorch_lightning/root_module/root_module.py

@@ -1,48 +1,28 @@
-import os
 import torch
-import math
 
 from pytorch_lightning.root_module.memory import ModelSummary
 from pytorch_lightning.root_module.grads import GradInformation
 from pytorch_lightning.root_module.model_saving import ModelIO, load_hparams_from_tags_csv
-from pytorch_lightning.root_module.optimization import OptimizerConfig
 from pytorch_lightning.root_module.hooks import ModelHooks
+from pytorch_lightning.root_module.decorators import data_loader
 
 
+class LightningModule(GradInformation, ModelIO, ModelHooks):
 
-class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
-
-    def __init__(self, hparams):
-        super(LightningModule, self).__init__()
-        self.hparams = hparams
+    def __init__(self, *args, **kwargs):
+        super(LightningModule, self).__init__(*args, **kwargs)
 
         self.dtype = torch.FloatTensor
         self.exp_save_path = None
         self.current_epoch = 0
         self.global_step = 0
         self.loaded_optimizer_states_dict = {}
-        self.fast_dev_run = hparams.fast_dev_run
-        self.overfit = hparams.overfit
-        self.gradient_clip = hparams.gradient_clip
         self.trainer = None
-        self.from_lightning = True
         self.experiment = None
+        self.example_input_array = None
 
         # track if gpu was requested for checkpointing
         self.on_gpu = False
-        try:
-            self.on_gpu = hparams.on_gpu
-        except Exception as e:
-            pass
-
-        # computed vars for the dataloaders
-        self._tng_dataloader = None
-        self._val_dataloader = None
-        self._test_dataloader = None
-
-        if self.on_gpu:
-            print('running on gpu...')
-            torch.set_default_tensor_type(hparams.default_tensor_type)
 
     def forward(self, *args, **kwargs):
         """
@@ -56,18 +36,20 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
     def validation_step(self, data_batch, batch_nb):
         """
         return whatever outputs will need to be aggregated in validation_end
+        OPTIONAL
         :param data_batch:
         :return:
         """
-        raise NotImplementedError
+        pass
 
     def validation_end(self, outputs):
         """
         Outputs has the appended output after each validation step
+        OPTIONAL
         :param outputs:
         :return: dic_with_metrics for tqdm
         """
-        raise NotImplementedError
+        pass
 
     def training_step(self, data_batch, batch_nb):
         """
@@ -79,77 +61,34 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
 
     def configure_optimizers(self):
         """
-        Return array of optimizers
+        Return a list of optimizers and a list of schedulers (could be empty)
         :return:
         """
         raise NotImplementedError
 
-    def update_tng_log_metrics(self, logs):
-        """
-        Chance to update metrics to be logged for training step.
-        For example, add music, images, etc... to log
-        :param logs:
-        :return:
-        """
-        raise NotImplementedError
-
-    def loss(self, *args, **kwargs):
-        """
-        Expand model_out into your components
-        :param model_out:
-        :return:
-        """
-        raise NotImplementedError
-
-    def summarize(self):
-        model_summary = ModelSummary(self)
-        print(model_summary)
-
-    def nb_batches(self, dataloader):
-        a = math.ceil(float(len(dataloader.dataset) / self.batch_size))
-        return int(a)
-
-    def freeze(self):
-        for param in self.parameters():
-            param.requires_grad = False
-
-    def unfreeze(self):
-        for param in self.parameters():
-            param.requires_grad = True
-
-    @property
+    @data_loader
     def tng_dataloader(self):
         """
-        Implement a function to load an h5py of this data
+        Implement a PyTorch DataLoader
         :return:
         """
         raise NotImplementedError
 
-    @property
+    @data_loader
     def test_dataloader(self):
         """
-        Implement a function to load an h5py of this data
+        Implement a PyTorch DataLoader
         :return:
         """
-        raise NotImplementedError
+        return None
 
-    @property
+    @data_loader
     def val_dataloader(self):
         """
-        Implement a function to load an h5py of this data
+        Implement a PyTorch DataLoader
         :return:
         """
-        raise NotImplementedError
-
-    @staticmethod
-    def get_process_position(gpus):
-        try:
-            current_gpu = os.environ["CUDA_VISIBLE_DEVICES"]
-            gpu_ids = gpus.split(';')
-            process_position = gpu_ids.index(current_gpu)
-            return process_position, current_gpu
-        except Exception as e:
-            return 0, 0
+        return None
 
     @classmethod
     def load_from_metrics(cls, weights_path, tags_csv, on_gpu, map_location=None):
@@ -172,9 +111,23 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         else:
             checkpoint = torch.load(weights_path, map_location=lambda storage, loc: storage)
 
+        # load the state_dict on the model automatically
         model = cls(hparams)
+        model.load_state_dict(checkpoint['state_dict'])
+
+        # give model a chance to load something
+        model.on_load_checkpoint(checkpoint)
 
-        # allow model to load
-        model.load_model_specific(checkpoint)
-        model.load_state_dict(checkpoint['state_dict'], strict=False)
         return model
+
+    def summarize(self):
+        model_summary = ModelSummary(self)
+        print(model_summary)
+
+    def freeze(self):
+        for param in self.parameters():
+            param.requires_grad = False
+
+    def unfreeze(self):
+        for param in self.parameters():
+            param.requires_grad = True

pytorch_lightning/testing/__init__.py

@@ -0,0 +1,3 @@
+from .lm_test_module import LightningTestModel
+from .no_val_end_module import NoValEndTestModel
+from .no_val_module import NoValModel

pytorch_lightning/testing/lm_test_module.py

@@ -0,0 +1,275 @@
+import os
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.distributed import DistributedSampler
+from torchvision.datasets import MNIST
+from torchvision import transforms
+from test_tube import HyperOptArgumentParser
+
+from pytorch_lightning.root_module.root_module import LightningModule
+from pytorch_lightning import data_loader
+
+
+class LightningTestModel(LightningModule):
+    """
+    Sample model to show how to define a template
+    """
+
+    def __init__(self, hparams, force_remove_distributed_sampler=False):
+        """
+        Pass in parsed HyperOptArgumentParser to the model
+        :param hparams:
+        """
+        # init superclass
+        super(LightningTestModel, self).__init__()
+        self.hparams = hparams
+
+        self.batch_size = hparams.batch_size
+
+        # if you specify an example input, the summary will show input/output for each layer
+        self.example_input_array = torch.rand(5, 28 * 28)
+
+        # remove to test warning for dist sampler
+        self.force_remove_distributed_sampler = force_remove_distributed_sampler
+
+        # build model
+        self.__build_model()
+
+    # ---------------------
+    # MODEL SETUP
+    # ---------------------
+    def __build_model(self):
+        """
+        Layout model
+        :return:
+        """
+        self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+                              out_features=self.hparams.hidden_dim)
+        self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
+        self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
+
+        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+                              out_features=self.hparams.out_features)
+
+    # ---------------------
+    # TRAINING
+    # ---------------------
+    def forward(self, x):
+        """
+        No special modification required for lightning, define as you normally would
+        :param x:
+        :return:
+        """
+
+        x = self.c_d1(x)
+        x = torch.tanh(x)
+        x = self.c_d1_bn(x)
+        x = self.c_d1_drop(x)
+
+        x = self.c_d2(x)
+        logits = F.log_softmax(x, dim=1)
+
+        return logits
+
+    def loss(self, labels, logits):
+        nll = F.nll_loss(logits, labels)
+        return nll
+
+    def training_step(self, data_batch, batch_i):
+        """
+        Lightning calls this inside the training loop
+        :param data_batch:
+        :return:
+        """
+        # forward pass
+        x, y = data_batch
+        x = x.view(x.size(0), -1)
+
+        y_hat = self.forward(x)
+
+        # calculate loss
+        loss_val = self.loss(y, y_hat)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+
+        # alternate possible outputs to test
+        if self.trainer.batch_nb % 1 == 0:
+            output = OrderedDict({
+                'loss': loss_val,
+                'prog': {'some_val': loss_val * loss_val}
+            })
+            return output
+        if self.trainer.batch_nb % 2 == 0:
+            return loss_val
+
+    def validation_step(self, data_batch, batch_i, dataloader_i):
+        """
+        Lightning calls this inside the validation loop
+        :param data_batch:
+        :return:
+        """
+        x, y = data_batch
+        x = x.view(x.size(0), -1)
+        y_hat = self.forward(x)
+
+        loss_val = self.loss(y, y_hat)
+
+        # acc
+        labels_hat = torch.argmax(y_hat, dim=1)
+        val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+        val_acc = torch.tensor(val_acc)
+
+        if self.on_gpu:
+            val_acc = val_acc.cuda(loss_val.device.index)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+            val_acc = val_acc.unsqueeze(0)
+
+        # alternate possible outputs to test
+        if batch_i % 1 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+            })
+            return output
+        if batch_i % 2 == 0:
+            return val_acc
+
+        if batch_i % 3 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+                'test_dic': {'val_loss_a': loss_val}
+            })
+            return output
+        if batch_i % 5 == 0:
+            output = OrderedDict({
+                f'val_loss_{dataloader_i}': loss_val,
+                f'val_acc_{dataloader_i}': val_acc,
+            })
+            return output
+
+    def validation_end(self, outputs):
+        """
+        Called at the end of validation to aggregate outputs
+        :param outputs: list of individual outputs of each validation step
+        :return:
+        """
+        # if returned a scalar from validation_step, outputs is a list of tensor scalars
+        # we return just the average in this case (if we want)
+        # return torch.stack(outputs).mean()
+
+        val_loss_mean = 0
+        val_acc_mean = 0
+        for output in outputs:
+            val_loss_mean += output['val_loss']
+            val_acc_mean += output['val_acc']
+
+        val_loss_mean /= len(outputs)
+        val_acc_mean /= len(outputs)
+
+        tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()}
+        return tqdm_dic
+
+    def on_tng_metrics(self, logs):
+        logs['some_tensor_to_test'] = torch.rand(1)
+
+    # ---------------------
+    # TRAINING SETUP
+    # ---------------------
+    def configure_optimizers(self):
+        """
+        return whatever optimizers we want here
+        :return: list of optimizers
+        """
+        # try no scheduler for this model (testing purposes)
+        optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
+
+        # test returning only 1 list instead of 2
+        return [optimizer]
+
+    def __dataloader(self, train):
+        # init data generators
+        transform = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize((0.5,), (1.0,))])
+        dataset = MNIST(root=self.hparams.data_root, train=train,
+                        transform=transform, download=True)
+
+        # when using multi-node we need to add the datasampler
+        train_sampler = None
+        batch_size = self.hparams.batch_size
+
+        try:
+            if self.on_gpu and not self.force_remove_distributed_sampler:
+                train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
+                batch_size = batch_size // self.trainer.world_size  # scale batch size
+        except Exception:
+            pass
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
+            dataset=dataset,
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler
+        )
+
+        return loader
+
+    @data_loader
+    def tng_dataloader(self):
+        return self.__dataloader(train=True)
+
+    @data_loader
+    def val_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @data_loader
+    def test_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @staticmethod
+    def add_model_specific_args(parent_parser, root_dir):  # pragma: no cover
+        """
+        Parameters you define here will be available to your model through self.hparams
+        :param parent_parser:
+        :param root_dir:
+        :return:
+        """
+        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
+
+        # param overwrites
+        # parser.set_defaults(gradient_clip=5.0)
+
+        # network params
+        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
+        parser.add_argument('--in_features', default=28 * 28, type=int)
+        parser.add_argument('--out_features', default=10, type=int)
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
+
+        # data
+        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
+
+        # training params (opt)
+        parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+                        options=[0.0001, 0.0005, 0.001, 0.005],
+                        tunable=False)
+        parser.opt_list('--optimizer_name', default='adam', type=str,
+                        options=['adam'], tunable=False)
+
+        # if using 2 nodes with 4 gpus each the batch size here
+        #  (256) will be 256 / (2*8) = 16 per gpu
+        parser.opt_list('--batch_size', default=256 * 8, type=int,
+                        options=[32, 64, 128, 256], tunable=False,
+                        help='batch size will be divided over all gpus being used across all nodes')
+        return parser

pytorch_lightning/testing/no_val_end_module.py

@@ -0,0 +1,247 @@
+import os
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.distributed import DistributedSampler
+from torchvision.datasets import MNIST
+from torchvision import transforms
+from test_tube import HyperOptArgumentParser
+
+from pytorch_lightning.root_module.root_module import LightningModule
+from pytorch_lightning import data_loader
+
+
+class NoValEndTestModel(LightningModule):
+    """
+    Sample model to show how to define a template
+    """
+
+    def __init__(self, hparams, force_remove_distributed_sampler=False):
+        """
+        Pass in parsed HyperOptArgumentParser to the model
+        :param hparams:
+        """
+        # init superclass
+        super(NoValEndTestModel, self).__init__()
+        self.hparams = hparams
+
+        self.batch_size = hparams.batch_size
+
+        # if you specify an example input, the summary will show input/output for each layer
+        self.example_input_array = torch.rand(5, 28 * 28)
+
+        # remove to test warning for dist sampler
+        self.force_remove_distributed_sampler = force_remove_distributed_sampler
+
+        # build model
+        self.__build_model()
+
+    # ---------------------
+    # MODEL SETUP
+    # ---------------------
+    def __build_model(self):
+        """
+        Layout model
+        :return:
+        """
+        self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+                              out_features=self.hparams.hidden_dim)
+        self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
+        self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
+
+        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+                              out_features=self.hparams.out_features)
+
+    # ---------------------
+    # TRAINING
+    # ---------------------
+    def forward(self, x):
+        """
+        No special modification required for lightning, define as you normally would
+        :param x:
+        :return:
+        """
+
+        x = self.c_d1(x)
+        x = torch.tanh(x)
+        x = self.c_d1_bn(x)
+        x = self.c_d1_drop(x)
+
+        x = self.c_d2(x)
+        logits = F.log_softmax(x, dim=1)
+
+        return logits
+
+    def loss(self, labels, logits):
+        nll = F.nll_loss(logits, labels)
+        return nll
+
+    def training_step(self, data_batch, batch_i):
+        """
+        Lightning calls this inside the training loop
+        :param data_batch:
+        :return:
+        """
+        # forward pass
+        x, y = data_batch
+        x = x.view(x.size(0), -1)
+
+        y_hat = self.forward(x)
+
+        # calculate loss
+        loss_val = self.loss(y, y_hat)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+
+        # alternate possible outputs to test
+        if self.trainer.batch_nb % 1 == 0:
+            output = OrderedDict({
+                'loss': loss_val,
+                'prog': {'some_val': loss_val * loss_val}
+            })
+            return output
+        if self.trainer.batch_nb % 2 == 0:
+            return loss_val
+
+    def validation_step(self, data_batch, batch_i, dataloader_i):
+        """
+        Lightning calls this inside the validation loop
+        :param data_batch:
+        :return:
+        """
+        x, y = data_batch
+        x = x.view(x.size(0), -1)
+        y_hat = self.forward(x)
+
+        loss_val = self.loss(y, y_hat)
+
+        # acc
+        labels_hat = torch.argmax(y_hat, dim=1)
+        val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+        val_acc = torch.tensor(val_acc)
+
+        if self.on_gpu:
+            val_acc = val_acc.cuda(loss_val.device.index)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+            val_acc = val_acc.unsqueeze(0)
+
+        # alternate possible outputs to test
+        if batch_i % 1 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+            })
+            return output
+        if batch_i % 2 == 0:
+            return val_acc
+
+        if batch_i % 3 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+                'test_dic': {'val_loss_a': loss_val}
+            })
+            return output
+
+    def on_tng_metrics(self, logs):
+        logs['some_tensor_to_test'] = torch.rand(1)
+
+    # ---------------------
+    # TRAINING SETUP
+    # ---------------------
+    def configure_optimizers(self):
+        """
+        return whatever optimizers we want here
+        :return: list of optimizers
+        """
+        # try no scheduler for this model (testing purposes)
+        optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
+
+        # test returning only 1 list instead of 2
+        return [optimizer]
+
+    def __dataloader(self, train):
+        # init data generators
+        transform = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize((0.5,), (1.0,))])
+        dataset = MNIST(root=self.hparams.data_root, train=train,
+                        transform=transform, download=True)
+
+        # when using multi-node we need to add the datasampler
+        train_sampler = None
+        batch_size = self.hparams.batch_size
+
+        try:
+            if self.on_gpu and not self.force_remove_distributed_sampler:
+                train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
+                batch_size = batch_size // self.trainer.world_size  # scale batch size
+        except Exception:
+            pass
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
+            dataset=dataset,
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler
+        )
+
+        return loader
+
+    @data_loader
+    def tng_dataloader(self):
+        return self.__dataloader(train=True)
+
+    @data_loader
+    def val_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @data_loader
+    def test_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @staticmethod
+    def add_model_specific_args(parent_parser, root_dir):  # pragma: no cover
+        """
+        Parameters you define here will be available to your model through self.hparams
+        :param parent_parser:
+        :param root_dir:
+        :return:
+        """
+        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
+
+        # param overwrites
+        # parser.set_defaults(gradient_clip=5.0)
+
+        # network params
+        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
+        parser.add_argument('--in_features', default=28 * 28, type=int)
+        parser.add_argument('--out_features', default=10, type=int)
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
+
+        # data
+        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
+
+        # training params (opt)
+        parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+                        options=[0.0001, 0.0005, 0.001, 0.005],
+                        tunable=False)
+        parser.opt_list('--optimizer_name', default='adam', type=str,
+                        options=['adam'], tunable=False)
+
+        # if using 2 nodes with 4 gpus each the batch size here
+        #  (256) will be 256 / (2*8) = 16 per gpu
+        parser.opt_list('--batch_size', default=256 * 8, type=int,
+                        options=[32, 64, 128, 256], tunable=False,
+                        help='batch size will be divided over all gpus being used across all nodes')
+        return parser

pytorch_lightning/testing/no_val_module.py

@@ -0,0 +1,196 @@
+import os
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.distributed import DistributedSampler
+from torchvision.datasets import MNIST
+from torchvision import transforms
+from test_tube import HyperOptArgumentParser
+
+from pytorch_lightning.root_module.root_module import LightningModule
+from pytorch_lightning import data_loader
+
+
+class NoValModel(LightningModule):
+    """
+    Sample model to show how to define a template
+    """
+
+    def __init__(self, hparams, force_remove_distributed_sampler=False):
+        """
+        Pass in parsed HyperOptArgumentParser to the model
+        :param hparams:
+        """
+        # init superclass
+        super(NoValModel, self).__init__()
+        self.hparams = hparams
+
+        self.batch_size = hparams.batch_size
+
+        # if you specify an example input, the summary will show input/output for each layer
+        self.example_input_array = torch.rand(5, 28 * 28)
+
+        # remove to test warning for dist sampler
+        self.force_remove_distributed_sampler = force_remove_distributed_sampler
+
+        # build model
+        self.__build_model()
+
+    # ---------------------
+    # MODEL SETUP
+    # ---------------------
+    def __build_model(self):
+        """
+        Layout model
+        :return:
+        """
+        self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+                              out_features=self.hparams.hidden_dim)
+        self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
+        self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
+
+        self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+                              out_features=self.hparams.out_features)
+
+    # ---------------------
+    # TRAINING
+    # ---------------------
+    def forward(self, x):
+        """
+        No special modification required for lightning, define as you normally would
+        :param x:
+        :return:
+        """
+
+        x = self.c_d1(x)
+        x = torch.tanh(x)
+        x = self.c_d1_bn(x)
+        x = self.c_d1_drop(x)
+
+        x = self.c_d2(x)
+        logits = F.log_softmax(x, dim=1)
+
+        return logits
+
+    def loss(self, labels, logits):
+        nll = F.nll_loss(logits, labels)
+        return nll
+
+    def training_step(self, data_batch, batch_i):
+        """
+        Lightning calls this inside the training loop
+        :param data_batch:
+        :return:
+        """
+        # forward pass
+        x, y = data_batch
+        x = x.view(x.size(0), -1)
+
+        y_hat = self.forward(x)
+
+        # calculate loss
+        loss_val = self.loss(y, y_hat)
+
+        # in DP mode (default) make sure if result is scalar, there's another dim in the beginning
+        if self.trainer.use_dp:
+            loss_val = loss_val.unsqueeze(0)
+
+        # alternate possible outputs to test
+        if self.trainer.batch_nb % 1 == 0:
+            output = OrderedDict({
+                'loss': loss_val,
+                'prog': {'some_val': loss_val * loss_val}
+            })
+            return output
+        if self.trainer.batch_nb % 2 == 0:
+            return loss_val
+
+    def on_tng_metrics(self, logs):
+        logs['some_tensor_to_test'] = torch.rand(1)
+
+    # ---------------------
+    # TRAINING SETUP
+    # ---------------------
+    def configure_optimizers(self):
+        """
+        return whatever optimizers we want here
+        :return: list of optimizers
+        """
+        # try no scheduler for this model (testing purposes)
+        optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
+
+        # test returning only 1 list instead of 2
+        return [optimizer]
+
+    def __dataloader(self, train):
+        # init data generators
+        transform = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize((0.5,), (1.0,))])
+        dataset = MNIST(root=self.hparams.data_root, train=train,
+                        transform=transform, download=True)
+
+        # when using multi-node we need to add the datasampler
+        train_sampler = None
+        batch_size = self.hparams.batch_size
+
+        try:
+            if self.on_gpu and not self.force_remove_distributed_sampler:
+                train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
+                batch_size = batch_size // self.trainer.world_size  # scale batch size
+        except Exception:
+            pass
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
+            dataset=dataset,
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler
+        )
+
+        return loader
+
+    @data_loader
+    def tng_dataloader(self):
+        return self.__dataloader(train=True)
+
+    @staticmethod
+    def add_model_specific_args(parent_parser, root_dir):  # pragma: no cover
+        """
+        Parameters you define here will be available to your model through self.hparams
+        :param parent_parser:
+        :param root_dir:
+        :return:
+        """
+        parser = HyperOptArgumentParser(strategy=parent_parser.strategy, parents=[parent_parser])
+
+        # param overwrites
+        # parser.set_defaults(gradient_clip=5.0)
+
+        # network params
+        parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
+        parser.add_argument('--in_features', default=28 * 28, type=int)
+        parser.add_argument('--out_features', default=10, type=int)
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
+
+        # data
+        parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
+
+        # training params (opt)
+        parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+                        options=[0.0001, 0.0005, 0.001, 0.005],
+                        tunable=False)
+        parser.opt_list('--optimizer_name', default='adam', type=str,
+                        options=['adam'], tunable=False)
+
+        # if using 2 nodes with 4 gpus each the batch size here
+        #  (256) will be 256 / (2*8) = 16 per gpu
+        parser.opt_list('--batch_size', default=256 * 8, type=int,
+                        options=[32, 64, 128, 256], tunable=False,
+                        help='batch size will be divided over all gpus being used across all nodes')
+        return parser

pytorch_lightning/trainer_main.py

@@ -1,214 +0,0 @@
-import os
-import sys
-
-import torch
-import numpy as np
-from test_tube import HyperOptArgumentParser, Experiment, SlurmCluster
-from pytorch_lightning.models.trainer import Trainer
-from pytorch_lightning.utils.arg_parse import add_default_args
-from time import sleep
-
-from pytorch_lightning.callbacks.pt_callbacks import EarlyStopping, ModelCheckpoint
-SEED = 2334
-torch.manual_seed(SEED)
-np.random.seed(SEED)
-
-# ---------------------
-# DEFINE MODEL HERE
-# ---------------------
-from pytorch_lightning.models.sample_model_template.model_template import ExampleModel1
-# ---------------------
-
-AVAILABLE_MODELS = {
-    'model_1': ExampleModel1
-}
-
-
-"""
-Allows training by using command line arguments
-
-Run by: 
-# TYPE YOUR RUN COMMAND HERE
-"""
-
-
-def main_local(hparams):
-    main(hparams, None, None)
-
-
-def main(hparams, cluster, results_dict):
-    """
-    Main training routine specific for this project
-    :param hparams:
-    :return:
-    """
-    on_gpu = torch.cuda.is_available()
-    if hparams.disable_cuda:
-        on_gpu = False
-
-    device = 'cuda' if on_gpu else 'cpu'
-    hparams.__setattr__('device', device)
-    hparams.__setattr__('on_gpu', on_gpu)
-    hparams.__setattr__('nb_gpus', torch.cuda.device_count())
-    hparams.__setattr__('inference_mode', hparams.model_load_weights_path is not None)
-
-    # delay each training start to not overwrite logs
-    process_position, current_gpu = TRAINING_MODEL.get_process_position(hparams.gpus)
-    sleep(process_position + 1)
-
-    # init experiment
-    exp = Experiment(
-        name=hparams.tt_name,
-        debug=hparams.debug,
-        save_dir=hparams.tt_save_path,
-        version=hparams.hpc_exp_number,
-        autosave=False,
-        description=hparams.tt_description
-    )
-
-    exp.argparse(hparams)
-    exp.save()
-
-    # build model
-    print('loading model...')
-    model = TRAINING_MODEL(hparams)
-    print('model built')
-
-    # callbacks
-    early_stop = EarlyStopping(
-        monitor=hparams.early_stop_metric,
-        patience=hparams.early_stop_patience,
-        verbose=True,
-        mode=hparams.early_stop_mode
-    )
-
-    model_save_path = '{}/{}/{}'.format(hparams.model_save_path, exp.name, exp.version)
-    checkpoint = ModelCheckpoint(
-        filepath=model_save_path,
-        save_function=None,
-        save_best_only=True,
-        verbose=True,
-        monitor=hparams.model_save_monitor_value,
-        mode=hparams.model_save_monitor_mode
-    )
-
-    # configure trainer
-    trainer = Trainer(
-        experiment=exp,
-        on_gpu=on_gpu,
-        cluster=cluster,
-        progress_bar=hparams.enable_tqdm,
-        overfit_pct=hparams.overfit,
-        track_grad_norm=hparams.track_grad_norm,
-        fast_dev_run=hparams.fast_dev_run,
-        check_val_every_n_epoch=hparams.check_val_every_n_epoch,
-        accumulate_grad_batches=hparams.accumulate_grad_batches,
-        process_position=process_position,
-        current_gpu_name=current_gpu,
-        checkpoint_callback=checkpoint,
-        early_stop_callback=early_stop,
-        enable_early_stop=hparams.enable_early_stop,
-        max_nb_epochs=hparams.max_nb_epochs,
-        min_nb_epochs=hparams.min_nb_epochs,
-        train_percent_check=hparams.train_percent_check,
-        val_percent_check=hparams.val_percent_check,
-        test_percent_check=hparams.test_percent_check,
-        val_check_interval=hparams.val_check_interval,
-        log_save_interval=hparams.log_save_interval,
-        add_log_row_interval=hparams.add_log_row_interval,
-        lr_scheduler_milestones=hparams.lr_scheduler_milestones
-    )
-
-    # train model
-    trainer.fit(model)
-
-
-def get_default_parser(strategy, root_dir):
-
-    possible_model_names = list(AVAILABLE_MODELS.keys())
-    parser = HyperOptArgumentParser(strategy=strategy, add_help=False)
-    add_default_args(parser, root_dir, possible_model_names, SEED)
-    return parser
-
-
-def get_model_name(args):
-    for i, arg in enumerate(args):
-        if 'model_name' in arg:
-            return args[i+1]
-
-
-def optimize_on_cluster(hyperparams):
-    # enable cluster training
-    cluster = SlurmCluster(
-        hyperparam_optimizer=hyperparams,
-        log_path=hyperparams.tt_save_path,
-        test_tube_exp_name=hyperparams.tt_name
-    )
-
-    # email for cluster coms
-    cluster.notify_job_status(email='add_email_here', on_done=True, on_fail=True)
-
-    # configure cluster
-    cluster.per_experiment_nb_gpus = hyperparams.per_experiment_nb_gpus
-    cluster.job_time = '48:00:00'
-    cluster.gpu_type = '1080ti'
-    cluster.memory_mb_per_node = 48000
-
-    # any modules for code to run in env
-    cluster.add_command('source activate pytorch_lightning')
-
-    # name of exp
-    job_display_name = hyperparams.tt_name.split('_')[0]
-    job_display_name = job_display_name[0:3]
-
-    # run hopt
-    print('submitting jobs...')
-    cluster.optimize_parallel_cluster_gpu(
-        main,
-        nb_trials=hyperparams.nb_hopt_trials,
-        job_name=job_display_name
-    )
-
-
-if __name__ == '__main__':
-
-    model_name = get_model_name(sys.argv)
-
-    # use default args
-    root_dir = os.path.split(os.path.dirname(sys.modules['__main__'].__file__))[0]
-    parent_parser = get_default_parser(strategy='random_search', root_dir=root_dir)
-
-    # allow model to overwrite or extend args
-    TRAINING_MODEL = AVAILABLE_MODELS[model_name]
-    parser = TRAINING_MODEL.add_model_specific_args(parent_parser)
-    parser.json_config('-c', '--config', default=root_dir + '/run_configs/local.json')
-    hyperparams = parser.parse_args()
-
-    # format GPU layout
-    os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
-    gpu_ids = hyperparams.gpus.split(';')
-
-    # RUN TRAINING
-    if hyperparams.on_cluster:
-        print('RUNNING ON SLURM CLUSTER')
-        os.environ["CUDA_VISIBLE_DEVICES"] = ','.join(gpu_ids)
-        optimize_on_cluster(hyperparams)
-
-    elif hyperparams.single_run_gpu:
-        print(f'RUNNING 1 TRIAL ON GPU. gpu: {gpu_ids[0]}')
-        os.environ["CUDA_VISIBLE_DEVICES"] = gpu_ids[0]
-        main(hyperparams, None, None)
-
-    elif hyperparams.local or hyperparams.single_run:
-        os.environ["CUDA_VISIBLE_DEVICES"] = '0'
-        print('RUNNING LOCALLY')
-        main(hyperparams, None, None)
-
-    else:
-        print(f'RUNNING MULTI GPU. GPU ids: {gpu_ids}')
-        hyperparams.optimize_parallel_gpu(
-            main_local,
-            gpu_ids=gpu_ids,
-            nb_trials=hyperparams.nb_hopt_trials,
-            nb_workers=len(gpu_ids)
-        )

pytorch_lightning/utilities/arg_parse.py

@@ -1,31 +1,48 @@
-import pdb
+"""
+List of default args which mught be useful for all the available flags
+Might need to update with the new flags
+"""
+
+import os
+
 
 def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None):
 
     # tng, test, val check intervals
-    parser.add_argument('--eval_test_set', dest='eval_test_set', action='store_true', help='true = run test set also')
-    parser.add_argument('--check_val_every_n_epoch', default=1, type=int, help='check val every n epochs')
+    parser.add_argument('--eval_test_set', dest='eval_test_set', action='store_true',
+                        help='true = run test set also')
+    parser.add_argument('--check_val_every_n_epoch', default=1, type=int,
+                        help='check val every n epochs')
     parser.opt_list('--accumulate_grad_batches', default=1, type=int, tunable=False,
-                    help='accumulates gradients k times before applying update. Simulates huge batch size')
+                    help='accumulates gradients k times before applying update.'
+                         ' Simulates huge batch size')
     parser.add_argument('--max_nb_epochs', default=200, type=int, help='cap epochs')
     parser.add_argument('--min_nb_epochs', default=2, type=int, help='min epochs')
-    parser.add_argument('--train_percent_check', default=1.0, type=float, help='how much of tng set to check')
-    parser.add_argument('--val_percent_check', default=1.0, type=float, help='how much of val set to check')
-    parser.add_argument('--test_percent_check', default=1.0, type=float, help='how much of test set to check')
+    parser.add_argument('--train_percent_check', default=1.0, type=float,
+                        help='how much of tng set to check')
+    parser.add_argument('--val_percent_check', default=1.0, type=float,
+                        help='how much of val set to check')
+    parser.add_argument('--test_percent_check', default=1.0, type=float,
+                        help='how much of test set to check')
 
-    parser.add_argument('--val_check_interval', default=0.95, type=float, help='how much within 1 epoch to check val')
-    parser.add_argument('--log_save_interval', default=100, type=int, help='how many batches between log saves')
-    parser.add_argument('--add_log_row_interval', default=100, type=int, help='add log every k batches')
+    parser.add_argument('--val_check_interval', default=0.95, type=float,
+                        help='how much within 1 epoch to check val')
+    parser.add_argument('--log_save_interval', default=100, type=int,
+                        help='how many batches between log saves')
+    parser.add_argument('--add_log_row_interval', default=100, type=int,
+                        help='add log every k batches')
 
     # early stopping
     parser.add_argument('--disable_early_stop', dest='enable_early_stop', action='store_false')
     parser.add_argument('--early_stop_metric', default='val_acc', type=str)
     parser.add_argument('--early_stop_mode', default='min', type=str)
-    parser.add_argument('--early_stop_patience', default=3, type=int, help='number of epochs until stop')
+    parser.add_argument('--early_stop_patience', default=3, type=int,
+                        help='number of epochs until stop')
 
     # gradient handling
     parser.add_argument('--gradient_clip', default=-1, type=int)
-    parser.add_argument('--track_grad_norm', default=-1, type=int, help='if > 0, will track this grad norm')
+    parser.add_argument('--track_grad_norm', default=-1, type=int,
+                        help='if > 0, will track this grad norm')
 
     # model saving
     parser.add_argument('--model_save_path', default=root_dir + '/model_weights')
@@ -39,9 +56,10 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
         parser.add_argument('--model_name', default='', help=','.join(possible_model_names))
 
     # test_tube settings
-    parser.add_argument('-en', '--tt_name', default='r_lib_')
-    parser.add_argument('-td', '--tt_description', default='test research  lib')
-    parser.add_argument('--tt_save_path', default=root_dir + '/test_tube_logs', help='logging dir')
+    parser.add_argument('-en', '--tt_name', default='pt_test')
+    parser.add_argument('-td', '--tt_description', default='pytorch lightning test')
+    parser.add_argument('--tt_save_path', default=os.path.join(root_dir, 'test_tube_logs'),
+                        help='logging dir')
     parser.add_argument('--enable_single_run', dest='single_run', action='store_true')
     parser.add_argument('--nb_hopt_trials', default=1, type=int)
     parser.add_argument('--log_stdout', dest='log_stdout', action='store_true')
@@ -52,25 +70,30 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
     parser.add_argument('--default_tensor_type', default='torch.cuda.FloatTensor', type=str)
     parser.add_argument('--use_amp', dest='use_amp', action='store_true')
     parser.add_argument('--check_grad_nans', dest='check_grad_nans', action='store_true')
-    parser.add_argument('--amp_level', default='O2',type=str)
-
+    parser.add_argument('--amp_level', default='O2', type=str)
 
     # run on hpc
     parser.add_argument('--on_cluster', dest='on_cluster', action='store_true')
 
     # FAST training
     # use these settings to make sure network has no bugs without running a full dataset
-    parser.add_argument('--fast_dev_run', dest='fast_dev_run', default=False, action='store_true', help='runs validation after 1 tng step')
-    parser.add_argument('--enable_tqdm', dest='enable_tqdm', default=False, action='store_true', help='false removes the prog bar')
-    parser.add_argument('--overfit', default=-1, type=float, help='% of dataset to use with this option. float, or -1 for none')
+    parser.add_argument('--fast_dev_run', dest='fast_dev_run', default=False, action='store_true',
+                        help='runs validation after 1 tng step')
+    parser.add_argument('--enable_tqdm', dest='enable_tqdm', default=False, action='store_true',
+                        help='false removes the prog bar')
+    parser.add_argument('--overfit', default=-1, type=float,
+                        help='% of dataset to use with this option. float, or -1 for none')
 
     # debug args
     if rand_seed is not None:
         parser.add_argument('--random_seed', default=rand_seed, type=int)
 
-    parser.add_argument('--interactive', dest='interactive', action='store_true', help='runs on gpu without cluster')
-    parser.add_argument('--debug', dest='debug', action='store_true', help='enables/disables test tube')
-    parser.add_argument('--local', dest='local', action='store_true', help='enables local tng')
+    parser.add_argument('--interactive', dest='interactive', action='store_true',
+                        help='runs on gpu without cluster')
+    parser.add_argument('--debug', dest='debug', action='store_true',
+                        help='enables/disables test tube')
+    parser.add_argument('--local', dest='local', action='store_true',
+                        help='enables local tng')
 
     # optimizer
-    parser.add_argument('--lr_scheduler_milestones', default=None, type=str)
+    parser.add_argument('--lr_scheduler_milestones', default=None, type=str)

pytorch_lightning/utilities/debugging.py

@@ -0,0 +1,2 @@
+class MisconfigurationException(Exception):
+    pass

pytorch_lightning/utils/embeddings.py

@@ -1,104 +0,0 @@
-import torch
-import numpy as np
-from copy import deepcopy
-
-
-class PretrainedEmbedding(torch.nn.Embedding):
-
-    def __init__(self, embedding_path, embedding_dim, task_vocab, freeze=True, *args, **kwargs):
-        """
-        Loads a prebuilt pytorch embedding from any embedding formated file.
-        Padding=0 by default.
-
-        >>> emb = PretrainedEmbedding(embedding_path='glove.840B.300d.txt',embedding_dim=300, task_vocab={'hello': 1, 'world': 2})
-        >>> data = torch.Tensor([[0, 1], [0, 2]]).long()
-        >>> embedded = emb(data)
-        
-
-
-        :param embedding_path:
-        :param emb_dim:
-        :param task_vocab:
-        :param freeze:
-        :return:
-        """
-        # count the vocab
-        self.vocab_size = max(task_vocab.values()) + 1
-        super(PretrainedEmbedding, self).__init__(self.vocab_size, embedding_dim, padding_idx=0, *args, **kwargs)
-
-        # load pretrained embeddings
-        new_emb = self.__load_task_specific_embeddings(deepcopy(task_vocab), embedding_path, embedding_dim, freeze)
-
-        # transfer weights
-        self.weight = new_emb.weight
-
-        # apply freeze
-        should_freeze = not freeze
-        self.weight.requires_grad = should_freeze
-
-    def __load_task_specific_embeddings(self, vocab_words, embedding_path, emb_dim, freeze):
-        """
-        Iterates embedding file to only pull out task specific embeddings
-        :param vocab_words:
-        :param embedding_path:
-        :param emb_dim:
-        :param freeze:
-        :return:
-        """
-
-        # holds final embeddings for relevant words
-        embeddings = np.zeros(shape=(self.vocab_size, emb_dim))
-
-        # load embedding line by line and extract relevant embeddings
-        with open(embedding_path, encoding='utf-8') as f:
-            for line in f:
-                tokens = line.split(' ')
-                word = tokens[0]
-                embedding = tokens[1:]
-                embedding[-1] = embedding[-1][:-1]  # remove last new line
-
-                if word in vocab_words:
-                    vocab_word_i = vocab_words[word]
-
-                    # skip words that try to overwrite pad idx
-                    if vocab_word_i == 0:
-                        del vocab_words[word]
-                        continue
-
-                    emb_vals = np.asarray([float(x) for x in embedding])
-                    embeddings[vocab_word_i] = emb_vals
-
-                    # remove vocab word to early terminate
-                    del vocab_words[word]
-
-                # early break
-                if len(vocab_words) == 0:
-                    break
-
-        # add random vectors for the non-pretrained words
-        # these are vocab words NOT found in the pretrained embeddings
-        for w, i in vocab_words.items():
-            # skip words that try to overwrite pad idx
-            if i == 0:
-                continue
-
-            embedding = np.random.normal(size=emb_dim)
-            embeddings[i] = embedding
-
-        # turn into pt embedding
-        embeddings = torch.FloatTensor(embeddings)
-        embeddings = torch.nn.Embedding.from_pretrained(embeddings, freeze=freeze)
-
-        return embeddings
-
-
-if __name__ == '__main__':
-    emb = PretrainedEmbedding(
-        embedding_path='/Users/waf/Developer',
-        embedding_dim=300,
-        task_vocab={'hello': 1, 'world': 2}
-    )
-
-    data = torch.Tensor([[0, 1], [0, 2]]).long()
-    embedded = emb(data)
-    print(embedded)

pytorch_lightning/utils/plotting.py

@@ -1,28 +0,0 @@
-from matplotlib import pyplot as plt
-import numpy as np
-np.seterr(divide='ignore', invalid='ignore')
-
-
-def plot_confusion_matrix(cm,
-                          save_path,
-                          normalize=False,
-                          title='Confusion matrix',
-                          ylabel='y',
-                          xlabel='x'):
-    """
-    This function prints and plots the confusion matrix.
-    Normalization can be applied by setting `normalize=True`.
-    """
-    if normalize:
-        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
-        print("Normalized confusion matrix")
-    else:
-        print('Confusion matrix, without normalization')
-
-    fig = plt.figure()
-    plt.matshow(cm)
-    plt.title(title)
-    plt.colorbar()
-    plt.ylabel(ylabel)
-    plt.xlabel(xlabel)
-    plt.savefig(save_path)

requirements.txt

@@ -1,35 +1,7 @@
-
-atomicwrites==1.2.1
-attrs==18.2.0
-certifi==2018.11.29
-cffi==1.11.5
-imageio==2.4.1
-mkl-fft==1.0.6
-mkl-random==1.0.2
-more-itertools==5.0.0
-numpy==1.15.4
-olefile==0.46
-pandas==0.23.4
-Pillow==5.3.0
-pluggy==0.8.0
-py==1.7.0
-pycparser==2.19
-pytest==4.0.2
-python-dateutil==2.7.5
-pytz==2018.7
 scikit-learn==0.20.2
-scipy==1.2.0
-six==1.12.0
-sklearn==0.0
-tensorboard==1.14.0
-tensorboardX==1.7
-tensorflow==1.14.0
-test-tube==0.643
-torch==1.0.0
-torchvision==0.2.1
 tqdm==4.32.1
 twine==1.13.0
-urllib3==1.25.3
-webencodings==0.5.1
-Werkzeug==0.15.4
-wrapt==1.11.2
+numpy==1.16.4
+torch>=1.1.0
+torchvision>=0.3.0
+pandas

setup.cfg

@@ -16,6 +16,36 @@ markers =
 ignore = E731,W504
 max-line-length = 120
 
+[coverage:report]
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    if self.debug:
+    if settings.DEBUG
+    raise AssertionError
+    raise NotImplementedError
+    if 0:
+    if __name__ == .__main__.:
+    except Exception as e
+    print(e)
+    print(traceback.print_exc())
+    return *
+    raise Exception
+    raise *
+    except *
+    warnings
+    print
+    raise RuntimeError
+    break
+    pass
+    os.makedirs
+
+omit =
+    pytorch_lightning/callbacks/pt_callbacks.py
+    tests/test_models.py
+    pytorch_lightning/testing_models/lm_test_module.py
+    pytorch_lightning/utilities/arg_parse.py
+
 [flake8]
 ignore = E731,W504,F401,F841
 max-line-length = 120

setup.py

@@ -1,30 +1,58 @@
 #!/usr/bin/env python
 
+# Always prefer setuptools over distutils
 from setuptools import setup, find_packages
 
 # https://packaging.python.org/guides/single-sourcing-package-version/
 
 # http://blog.ionelmc.ro/2014/05/25/python-packaging/
+
+# https://packaging.python.org/discussions/install-requires-vs-requirements /
+# keep the meta-data here for simplicity in reading this file... it's not obvious
+# what happens and to non-engineers they won't know to look in init ...
+# the goal of the project is simplicity for researchers, don't want to add too much
+# engineer specific practices
 setup(
-    name="pytorch-lightning",
-    version='0.121',
-    description="The Keras for ML researchers using PyTorch",
-    author="William Falcon",
-    author_email="waf2107@columbia.edu",
-    url="https://github.com/williamFalcon/pytorch-lightning",
-    download_url="https://github.com/williamFalcon/pytorch-lightning",
-    license="MIT",
-    keywords=["deep learning", "pytorch", "AI"],
-    python_requires=">=3.5",
-    install_requires=[
-        "torch>=1.1.0",
-        "tqdm",
-        "test-tube>=0.651",
-        "tensorflow>=1.14.0"
-    ],
+    name='pytorch-lightning',
+    version='0.4.4',
+    description='The Keras for ML researchers using PyTorch',
+    author='William Falcon',
+    author_email='waf2107@columbia.edu',
+    url='https://github.com/williamFalcon/pytorch-lightning',
+    download_url='https://github.com/williamFalcon/pytorch-lightning',
+    license='Apache-2',
     packages=find_packages(),
-    long_description=open("README.md", encoding="utf-8").read(),
+    long_description=open('README.md', encoding='utf-8').read(),
     long_description_content_type='text/markdown',
     include_package_data=True,
     zip_safe=False,
+    keywords=['deep learning', 'pytorch', 'AI'],
+    python_requires='>=3.6',
+    install_requires=[
+        'torch==1.2.0',
+        'tqdm',
+        'test-tube>=0.6.9',
+        'pandas>=0.20.3',
+    ],
+    classifiers=[
+        'Environment :: Console',
+        'Natural Language :: English',
+        # How mature is this project? Common values are
+        #   3 - Alpha, 4 - Beta, 5 - Production/Stable
+        'Development Status :: 4 - Beta',
+        # Indicate who your project is intended for
+        'Intended Audience :: Developers',
+        'Topic :: Scientific/Engineering :: Artificial Intelligence',
+        'Topic :: Scientific/Engineering :: Image Recognition',
+        'Topic :: Scientific/Engineering :: Information Analysis',
+        # Pick your license as you wish
+        'License :: OSI Approved :: BSD License',
+        'Operating System :: OS Independent',
+        # Specify the Python versions you support here. In particular, ensure
+        # that you indicate whether you support Python 2, Python 3 or both.
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+    ],
 )

tests/README.md

@@ -0,0 +1,63 @@
+# PyTorch-Lightning Tests
+
+## Running tests
+The automatic travis tests ONLY run CPU-based tests. Although these cover most of the use cases,
+run on a 2-GPU machine to validate the full test-suite.
+
+
+To run all tests do the following:
+```bash
+git clone https://github.com/williamFalcon/pytorch-lightning
+cd pytorch-lightning
+
+# install module locally
+pip install -e .
+
+# install dev deps
+pip install -r requirements.txt
+
+# run tests
+py.test -v
+```
+
+To test models that require GPU make sure to run the above command on a GPU machine.
+The GPU machine must have:
+1. At least 2 GPUs.
+2. [NVIDIA-apex](https://github.com/NVIDIA/apex#linux) installed.
+
+
+### test_models.py
+This file fits a tiny model on MNIST using these different set-ups.
+1. CPU only.
+2. Single GPU with DP.
+3. Multiple (2) GPUs using DP.
+3. Multiple (2) GPUs using DDP.
+3. Multiple (2) GPUs using DP + apex (for 16-bit precision).
+3. Multiple (2) GPUs using DDP + apex (for 16-bit precision).   
+
+For each set up it also tests:
+1. model saving.
+2. model loading.
+3. predicting with a loaded model.
+4. simulated save from HPC signal.
+5. simulated load from HPC signal.
+
+## Running Coverage   
+Make sure to run coverage on a GPU machine with at least 2 GPUs and NVIDIA apex installed. 
+
+```bash
+cd pytorch-lightning
+
+# generate coverage 
+pip install coverage
+coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
+
+# print coverage stats
+coverage report -m
+
+# exporting resulys
+coverage xml
+codecov -t 17327163-8cca-4a5d-86c8-ca5f2ef700bc  -v
+```
+
+

tests/debug.py

@@ -0,0 +1,176 @@
+from pytorch_lightning import Trainer
+from examples import LightningTemplateModel
+from argparse import Namespace
+from test_tube import Experiment
+from pytorch_lightning.callbacks import ModelCheckpoint
+import os
+import shutil
+
+import pytorch_lightning as pl
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+
+
+class CoolModel(pl.LightningModule):
+
+    def __init(self):
+        super(CoolModel, self).__init__()
+        # not the best model...
+        self.l1 = torch.nn.Linear(28 * 28, 10)
+
+    def forward(self, x):
+        return torch.relu(self.l1(x))
+
+    def my_loss(self, y_hat, y):
+        return F.cross_entropy(y_hat, y)
+
+    def training_step(self, batch, batch_nb):
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'tng_loss': self.my_loss(y_hat, y)}
+
+    def validation_step(self, batch, batch_nb):
+        x, y = batch
+        y_hat = self.forward(x)
+        return {'val_loss': self.my_loss(y_hat, y)}
+
+    def validation_end(self, outputs):
+        avg_loss = torch.stack([x for x in outputs['val_loss']]).mean()
+        return avg_loss
+
+    def configure_optimizers(self):
+        return [torch.optim.Adam(self.parameters(), lr=0.02)]
+
+    @pl.data_loader
+    def tng_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=True), batch_size=32)
+
+    @pl.data_loader
+    def val_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+
+    @pl.data_loader
+    def test_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+
+
+def get_model():
+    # set up model with these hyperparams
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    hparams = Namespace(**{'drop_prob': 0.2,
+                           'batch_size': 32,
+                           'in_features': 28 * 28,
+                           'learning_rate': 0.001 * 8,
+                           'optimizer_name': 'adam',
+                           'data_root': os.path.join(root_dir, 'mnist'),
+                           'out_features': 10,
+                           'hidden_dim': 1000})
+    model = LightningTemplateModel(hparams)
+
+    return model, hparams
+
+
+def get_exp(debug=True):
+    # set up exp object without actually saving logs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    exp = Experiment(debug=debug, save_dir=root_dir, name='tests_tt_dir')
+    return exp
+
+
+def init_save_dir():
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    save_dir = os.path.join(root_dir, 'save_dir')
+
+    if os.path.exists(save_dir):
+        shutil.rmtree(save_dir)
+
+    os.makedirs(save_dir, exist_ok=True)
+
+    return save_dir
+
+
+def clear_save_dir():
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    save_dir = os.path.join(root_dir, 'save_dir')
+    if os.path.exists(save_dir):
+        shutil.rmtree(save_dir)
+
+
+def load_model(exp, save_dir):
+
+    # load trained model
+    tags_path = exp.get_data_path(exp.name, exp.version)
+    tags_path = os.path.join(tags_path, 'meta_tags.csv')
+
+    checkpoints = [x for x in os.listdir(save_dir) if '.ckpt' in x]
+    weights_dir = os.path.join(save_dir, checkpoints[0])
+
+    trained_model = LightningTemplateModel.load_from_metrics(weights_path=weights_dir,
+                                                             tags_csv=tags_path, on_gpu=True)
+
+    assert trained_model is not None, 'loading model failed'
+
+    return trained_model
+
+
+def run_prediction(dataloader, trained_model):
+    # run prediction on 1 batch
+    for batch in dataloader:
+        break
+
+    x, y = batch
+    x = x.view(x.size(0), -1)
+
+    y_hat = trained_model(x)
+
+    # acc
+    labels_hat = torch.argmax(y_hat, dim=1)
+    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+    val_acc = torch.tensor(val_acc)
+    val_acc = val_acc.item()
+
+    print(val_acc)
+
+    assert val_acc > 0.70, 'this model is expected to get > 0.7 in test set (it got %f)' % val_acc
+
+
+def main():
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.save()
+
+    # exp file to get weights
+    checkpoint = ModelCheckpoint(save_dir)
+
+    trainer = Trainer(
+        experiment=exp,
+        checkpoint_callback=checkpoint,
+        progress_bar=True,
+        max_nb_epochs=1,
+        gpus=[0, 1],
+        distributed_backend='dp',
+    )
+
+    model = CoolModel()
+
+    result = trainer.fit(model)
+
+    # correct result and ok accuracy
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # test model loading
+    pretrained_model = load_model(exp, save_dir)
+
+    # test model preds
+    run_prediction(model.test_dataloader, pretrained_model)
+
+    clear_save_dir()
+
+
+if __name__ == '__main__':
+    main()

tests/requirements.txt

@@ -0,0 +1,8 @@
+tox
+coverage
+codecov
+pytest>=3.0.5
+pytest-cov
+flake8
+check-manifest
+test_tube

tests/test_models.py

@@ -0,0 +1,944 @@
+import os
+import shutil
+import warnings
+from argparse import Namespace
+
+import pytest
+import numpy as np
+import torch
+from test_tube import Experiment, SlurmCluster
+
+# sys.path += [os.path.abspath('..'), os.path.abspath('../..')]
+from pytorch_lightning import Trainer
+from pytorch_lightning.testing import LightningTestModel, NoValEndTestModel, NoValModel
+from pytorch_lightning.callbacks import ModelCheckpoint, EarlyStopping
+from pytorch_lightning.utilities.debugging import MisconfigurationException
+from pytorch_lightning.root_module import memory
+from pytorch_lightning.models.trainer import reduce_distributed_output
+from pytorch_lightning.root_module import model_saving
+from examples import LightningTemplateModel
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+# ------------------------------------------------------------------------
+# TESTS
+# ------------------------------------------------------------------------
+
+def test_early_stopping_cpu_model():
+    """
+    Test each of the trainer options
+    :return:
+    """
+
+    stopping = EarlyStopping(monitor='val_loss')
+    trainer_options = dict(
+        early_stop_callback=stopping,
+        gradient_clip=1.0,
+        overfit_pct=0.20,
+        track_grad_norm=2,
+        print_nan_grads=True,
+        progress_bar=False,
+        experiment=get_exp(),
+        train_percent_check=0.1,
+        val_percent_check=0.1
+    )
+
+    model, hparams = get_model()
+    run_gpu_model_test(trainer_options, model, hparams, on_gpu=False)
+
+    # test freeze on cpu
+    model.freeze()
+    model.unfreeze()
+
+
+def test_no_val_module():
+    """
+    Tests use case where trainer saves the model, and user loads it from tags independently
+    :return:
+    """
+    hparams = get_hparams()
+    model = NoValModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    trainer_options = dict(
+        max_nb_epochs=1,
+        cluster=SlurmCluster(),
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir)
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # save model
+    new_weights_path = os.path.join(save_dir, 'save_test.ckpt')
+    trainer.save_checkpoint(new_weights_path)
+
+    # load new model
+    tags_path = exp.get_data_path(exp.name, exp.version)
+    tags_path = os.path.join(tags_path, 'meta_tags.csv')
+    model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path,
+                                                   tags_csv=tags_path, on_gpu=False)
+    model_2.eval()
+
+    # make prediction
+    clear_save_dir()
+
+
+def test_no_val_end_module():
+    """
+    Tests use case where trainer saves the model, and user loads it from tags independently
+    :return:
+    """
+    hparams = get_hparams()
+    model = NoValEndTestModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    trainer_options = dict(
+        max_nb_epochs=1,
+        cluster=SlurmCluster(),
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir)
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # save model
+    new_weights_path = os.path.join(save_dir, 'save_test.ckpt')
+    trainer.save_checkpoint(new_weights_path)
+
+    # load new model
+    tags_path = exp.get_data_path(exp.name, exp.version)
+    tags_path = os.path.join(tags_path, 'meta_tags.csv')
+    model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path,
+                                                   tags_csv=tags_path, on_gpu=False)
+    model_2.eval()
+
+    # make prediction
+    clear_save_dir()
+
+
+def test_simple_cpu():
+    """
+    Verify continue training session on CPU
+    :return:
+    """
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    trainer_options = dict(
+        max_nb_epochs=1,
+        val_percent_check=0.1,
+        train_percent_check=0.1,
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    clear_save_dir()
+
+
+def test_amp_single_gpu():
+    """
+    Make sure DDP + AMP work
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      'Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      'Rerun on a node with 2+ GPUs to run this test')
+        return
+
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    trainer_options = dict(
+        progress_bar=True,
+        max_nb_epochs=1,
+        gpus=[0],
+        distributed_backend='dp',
+        use_amp=True
+    )
+
+    run_gpu_model_test(trainer_options, model, hparams)
+
+
+def test_cpu_restore_training():
+    """
+    Verify continue training session on CPU
+    :return:
+    """
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    test_exp_version = 10
+    exp = get_exp(False, version=test_exp_version)
+    exp.argparse(hparams)
+    exp.save()
+
+    trainer_options = dict(
+        max_nb_epochs=2,
+        val_check_interval=0.50,
+        val_percent_check=0.2,
+        train_percent_check=0.2,
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir)
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+    real_global_epoch = trainer.current_epoch
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # wipe-out trainer and model
+    # retrain with not much data... this simulates picking training back up after slurm
+    # we want to see if the weights come back correctly
+    new_exp = get_exp(False, version=test_exp_version)
+    trainer_options = dict(
+        max_nb_epochs=2,
+        val_check_interval=0.50,
+        val_percent_check=0.2,
+        train_percent_check=0.2,
+        experiment=new_exp,
+        checkpoint_callback=ModelCheckpoint(save_dir),
+    )
+    trainer = Trainer(**trainer_options)
+    model = LightningTestModel(hparams)
+
+    # set the epoch start hook so we can predict before the model does the full training
+    def assert_good_acc():
+        assert trainer.current_epoch == real_global_epoch and trainer.current_epoch > 0
+
+        # if model and state loaded correctly, predictions will be good even though we
+        # haven't trained with the new loaded model
+        trainer.model.eval()
+        _ = [run_prediction(dataloader, trainer.model) for dataloader in trainer.val_dataloader]
+
+    model.on_sanity_check_start = assert_good_acc
+
+    # by calling fit again, we trigger training, loading weights from the cluster
+    # and our hook to predict using current model before any more weight updates
+    trainer.fit(model)
+
+    clear_save_dir()
+
+
+def test_amp_gpu_ddp():
+    """
+    Make sure DDP + AMP work
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      'Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      'Rerun on a node with 2+ GPUs to run this test')
+        return
+
+    os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
+
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    trainer_options = dict(
+        progress_bar=True,
+        max_nb_epochs=1,
+        gpus=[0, 1],
+        distributed_backend='ddp',
+        use_amp=True
+    )
+
+    run_gpu_model_test(trainer_options, model, hparams)
+
+
+def test_cpu_slurm_save_load():
+    """
+    Verify model save/load/checkpoint on CPU
+    :return:
+    """
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    cluster_a = SlurmCluster()
+    trainer_options = dict(
+        max_nb_epochs=1,
+        cluster=cluster_a,
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir)
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+    real_global_step = trainer.global_step
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # predict with trained model before saving
+    # make a prediction
+    for batch in model.test_dataloader:
+        break
+
+    x, y = batch
+    x = x.view(x.size(0), -1)
+
+    model.eval()
+    pred_before_saving = model(x)
+
+    # test registering a save function
+    trainer.enable_auto_hpc_walltime_manager()
+
+    # test HPC saving
+    # simulate snapshot on slurm
+    saved_filepath = trainer.hpc_save(save_dir, exp)
+    assert os.path.exists(saved_filepath)
+
+    # wipe-out trainer and model
+    # retrain with not much data... this simulates picking training back up after slurm
+    # we want to see if the weights come back correctly
+    continue_tng_hparams = get_hparams(continue_training=True,
+                                       hpc_exp_number=cluster_a.hpc_exp_number)
+    trainer_options = dict(
+        max_nb_epochs=1,
+        cluster=SlurmCluster(continue_tng_hparams),
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir),
+    )
+    trainer = Trainer(**trainer_options)
+    model = LightningTestModel(hparams)
+
+    # set the epoch start hook so we can predict before the model does the full training
+    def assert_pred_same():
+        assert trainer.global_step == real_global_step and trainer.global_step > 0
+
+        # predict with loaded model to make sure answers are the same
+        trainer.model.eval()
+        new_pred = trainer.model(x)
+        assert torch.all(torch.eq(pred_before_saving, new_pred)).item() == 1
+
+    model.on_epoch_start = assert_pred_same
+
+    # by calling fit again, we trigger training, loading weights from the cluster
+    # and our hook to predict using current model before any more weight updates
+    trainer.fit(model)
+
+    clear_save_dir()
+
+
+def test_loading_meta_tags():
+    hparams = get_hparams()
+
+    # save tags
+    exp = get_exp(False)
+    exp.tag({'some_str': 'a_str', 'an_int': 1, 'a_float': 2.0})
+    exp.argparse(hparams)
+    exp.save()
+
+    # load tags
+    tags_path = exp.get_data_path(exp.name, exp.version) + '/meta_tags.csv'
+    tags = model_saving.load_hparams_from_tags_csv(tags_path)
+
+    assert tags.batch_size == 32 and tags.hidden_dim == 1000
+
+    clear_save_dir()
+
+
+def test_dp_output_reduce():
+
+    # test identity when we have a single gpu
+    out = torch.rand(3, 1)
+    assert reduce_distributed_output(out, nb_gpus=1) is out
+
+    # average when we have multiples
+    assert reduce_distributed_output(out, nb_gpus=2) == out.mean()
+
+    # when we have a dict of vals
+    out = {
+        'a': out,
+        'b': {
+            'c': out
+        }
+    }
+    reduced = reduce_distributed_output(out, nb_gpus=3)
+    assert reduced['a'] == out['a']
+    assert reduced['b']['c'] == out['b']['c']
+
+
+def test_model_saving_loading():
+    """
+    Tests use case where trainer saves the model, and user loads it from tags independently
+    :return:
+    """
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    trainer_options = dict(
+        max_nb_epochs=1,
+        cluster=SlurmCluster(),
+        experiment=exp,
+        checkpoint_callback=ModelCheckpoint(save_dir)
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # traning complete
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # make a prediction
+    for batch in model.test_dataloader:
+        break
+
+    x, y = batch
+    x = x.view(x.size(0), -1)
+
+    # generate preds before saving model
+    model.eval()
+    pred_before_saving = model(x)
+
+    # save model
+    new_weights_path = os.path.join(save_dir, 'save_test.ckpt')
+    trainer.save_checkpoint(new_weights_path)
+
+    # load new model
+    tags_path = exp.get_data_path(exp.name, exp.version)
+    tags_path = os.path.join(tags_path, 'meta_tags.csv')
+    model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path,
+                                                   tags_csv=tags_path, on_gpu=False)
+    model_2.eval()
+
+    # make prediction
+    # assert that both predictions are the same
+    new_pred = model_2(x)
+    assert torch.all(torch.eq(pred_before_saving, new_pred)).item() == 1
+
+    clear_save_dir()
+
+
+def test_model_freeze_unfreeze():
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    model.freeze()
+    model.unfreeze()
+
+
+def test_amp_gpu_ddp_slurm_managed():
+    """
+    Make sure DDP + AMP work
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      ' Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_amp_gpu_ddp cannot run.'
+                      ' Rerun on a node with 2+ GPUs to run this test')
+        return
+
+    # simulate setting slurm flags
+    os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
+    os.environ['SLURM_LOCALID'] = str(0)
+
+    hparams = get_hparams()
+    model = LightningTestModel(hparams)
+
+    trainer_options = dict(
+        progress_bar=True,
+        max_nb_epochs=1,
+        gpus=[0],
+        distributed_backend='ddp',
+        use_amp=True
+    )
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    # exp file to get weights
+    checkpoint = ModelCheckpoint(save_dir)
+
+    # add these to the trainer options
+    trainer_options['checkpoint_callback'] = checkpoint
+    trainer_options['experiment'] = exp
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    trainer.is_slurm_managing_tasks = True
+    result = trainer.fit(model)
+
+    # correct result and ok accuracy
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # test root model address
+    assert trainer.resolve_root_node_address('abc') == 'abc'
+    assert trainer.resolve_root_node_address('abc[23]') == 'abc23'
+    assert trainer.resolve_root_node_address('abc[23-24]') == 'abc23'
+    assert trainer.resolve_root_node_address('abc[23-24, 45-40, 40]') == 'abc23'
+
+    # test model loading with a map_location
+    map_location = 'cuda:1'
+    pretrained_model = load_model(exp, save_dir, True, map_location)
+
+    # test model preds
+    run_prediction(model.test_dataloader, pretrained_model)
+
+    if trainer.use_ddp:
+        # on hpc this would work fine... but need to hack it for the purpose of the test
+        trainer.model = pretrained_model
+        trainer.optimizers, trainer.lr_schedulers = pretrained_model.configure_optimizers()
+
+    # test HPC loading / saving
+    trainer.hpc_save(save_dir, exp)
+    trainer.hpc_load(save_dir, on_gpu=True)
+
+    # test freeze on gpu
+    model.freeze()
+    model.unfreeze()
+
+    clear_save_dir()
+
+
+def test_cpu_model_with_amp():
+    """
+    Make sure model trains on CPU
+    :return:
+    """
+
+    trainer_options = dict(
+        progress_bar=False,
+        experiment=get_exp(),
+        max_nb_epochs=1,
+        train_percent_check=0.4,
+        val_percent_check=0.4,
+        use_amp=True
+    )
+
+    model, hparams = get_model()
+
+    with pytest.raises((MisconfigurationException, ModuleNotFoundError)):
+        run_gpu_model_test(trainer_options, model, hparams, on_gpu=False)
+
+
+def test_cpu_model():
+    """
+    Make sure model trains on CPU
+    :return:
+    """
+
+    trainer_options = dict(
+        progress_bar=False,
+        experiment=get_exp(),
+        max_nb_epochs=1,
+        train_percent_check=0.4,
+        val_percent_check=0.4
+    )
+
+    model, hparams = get_model()
+
+    run_gpu_model_test(trainer_options, model, hparams, on_gpu=False)
+
+
+def test_all_features_cpu_model():
+    """
+    Test each of the trainer options
+    :return:
+    """
+
+    trainer_options = dict(
+        gradient_clip=1.0,
+        overfit_pct=0.20,
+        track_grad_norm=2,
+        print_nan_grads=True,
+        progress_bar=False,
+        experiment=get_exp(),
+        accumulate_grad_batches=2,
+        max_nb_epochs=1,
+        train_percent_check=0.4,
+        val_percent_check=0.4
+    )
+
+    model, hparams = get_model()
+    run_gpu_model_test(trainer_options, model, hparams, on_gpu=False)
+
+
+def test_single_gpu_model():
+    """
+    Make sure single GPU works (DP mode)
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_single_gpu_model cannot run.'
+                      ' Rerun on a GPU node to run this test')
+        return
+    model, hparams = get_model()
+
+    trainer_options = dict(
+        progress_bar=False,
+        max_nb_epochs=1,
+        train_percent_check=0.1,
+        val_percent_check=0.1,
+        gpus=[0]
+    )
+
+    run_gpu_model_test(trainer_options, model, hparams)
+
+
+def test_multi_gpu_model_dp():
+    """
+    Make sure DP works
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_multi_gpu_model_dp cannot run.'
+                      ' Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_multi_gpu_model_dp cannot run.'
+                      ' Rerun on a node with 2+ GPUs to run this test')
+        return
+    model, hparams = get_model()
+    trainer_options = dict(
+        progress_bar=False,
+        max_nb_epochs=1,
+        train_percent_check=0.1,
+        val_percent_check=0.1,
+        gpus='-1'
+    )
+
+    run_gpu_model_test(trainer_options, model, hparams)
+
+    # test memory helper functions
+    memory.get_gpu_memory_map()
+
+
+def test_amp_gpu_dp():
+    """
+    Make sure DP + AMP work
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_amp_gpu_dp cannot run.'
+                      ' Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_amp_gpu_dp cannot run.'
+                      ' Rerun on a node with 2+ GPUs to run this test')
+        return
+    model, hparams = get_model()
+    trainer_options = dict(
+        max_nb_epochs=1,
+        gpus='0, 1',  # test init with gpu string
+        distributed_backend='dp',
+        use_amp=True
+    )
+    with pytest.raises(MisconfigurationException):
+        run_gpu_model_test(trainer_options, model, hparams)
+
+
+def test_multi_gpu_model_ddp():
+    """
+    Make sure DDP works
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_multi_gpu_model_ddp cannot run.'
+                      ' Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_multi_gpu_model_ddp cannot run.'
+                      ' Rerun on a node with 2+ GPUs to run this test')
+        return
+
+    os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
+    model, hparams = get_model()
+    trainer_options = dict(
+        progress_bar=False,
+        max_nb_epochs=1,
+        train_percent_check=0.4,
+        val_percent_check=0.2,
+        gpus=[0, 1],
+        distributed_backend='ddp'
+    )
+
+    run_gpu_model_test(trainer_options, model, hparams)
+
+
+def test_ddp_sampler_error():
+    """
+    Make sure DDP + AMP work
+    :return:
+    """
+    if not torch.cuda.is_available():
+        warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a GPU node to run this test')
+        return
+    if not torch.cuda.device_count() > 1:
+        warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a node with 2+ GPUs to run this test')
+        return
+
+    os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
+
+    hparams = get_hparams()
+    model = LightningTestModel(hparams, force_remove_distributed_sampler=True)
+
+    exp = get_exp(True)
+    exp.save()
+
+    trainer = Trainer(
+        experiment=exp,
+        progress_bar=False,
+        max_nb_epochs=1,
+        gpus=[0, 1],
+        distributed_backend='ddp',
+        use_amp=True
+    )
+
+    with pytest.warns(UserWarning):
+        trainer.get_dataloaders(model)
+
+    clear_save_dir()
+
+
+def test_multiple_val_dataloader():
+    """
+    Verify multiple val_dataloader
+    :return:
+    """
+    hparams = get_hparams()
+    model = LightningTemplateModel(hparams)
+
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    trainer_options = dict(
+        max_nb_epochs=1,
+        val_percent_check=0.1,
+        train_percent_check=0.1,
+    )
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # verify tng completed
+    assert result == 1
+
+    # verify there are 2 val loaders
+    assert len(trainer.val_dataloader) == 2, 'Multiple val_dataloaders not initiated properly'
+
+    # make sure predictions are good for each val set
+    [run_prediction(dataloader, trainer.model) for dataloader in trainer.val_dataloader]
+
+
+# ------------------------------------------------------------------------
+# UTILS
+# ------------------------------------------------------------------------
+def run_gpu_model_test(trainer_options, model, hparams, on_gpu=True):
+    save_dir = init_save_dir()
+
+    # exp file to get meta
+    exp = get_exp(False)
+    exp.argparse(hparams)
+    exp.save()
+
+    # exp file to get weights
+    checkpoint = ModelCheckpoint(save_dir)
+
+    # add these to the trainer options
+    trainer_options['checkpoint_callback'] = checkpoint
+    trainer_options['experiment'] = exp
+
+    # fit model
+    trainer = Trainer(**trainer_options)
+    result = trainer.fit(model)
+
+    # correct result and ok accuracy
+    assert result == 1, 'amp + ddp model failed to complete'
+
+    # test model loading
+    pretrained_model = load_model(exp, save_dir, on_gpu)
+
+    # test model preds
+    run_prediction(model.test_dataloader, pretrained_model)
+
+    if trainer.use_ddp:
+        # on hpc this would work fine... but need to hack it for the purpose of the test
+        trainer.model = pretrained_model
+        trainer.optimizers, trainer.lr_schedulers = pretrained_model.configure_optimizers()
+
+    # test HPC loading / saving
+    trainer.hpc_save(save_dir, exp)
+    trainer.hpc_load(save_dir, on_gpu=on_gpu)
+
+    clear_save_dir()
+
+
+def get_hparams(continue_training=False, hpc_exp_number=0):
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+
+    args = {
+        'drop_prob': 0.2,
+        'batch_size': 32,
+        'in_features': 28 * 28,
+        'learning_rate': 0.001 * 8,
+        'optimizer_name': 'adam',
+        'data_root': os.path.join(root_dir, 'mnist'),
+        'out_features': 10,
+        'hidden_dim': 1000}
+
+    if continue_training:
+        args['test_tube_do_checkpoint_load'] = True
+        args['hpc_exp_number'] = hpc_exp_number
+
+    hparams = Namespace(**args)
+    return hparams
+
+
+def get_model(use_test_model=False):
+    # set up model with these hyperparams
+    hparams = get_hparams()
+
+    if use_test_model:
+        model = LightningTestModel(hparams)
+    else:
+        model = LightningTemplateModel(hparams)
+
+    return model, hparams
+
+
+def get_exp(debug=True, version=None):
+    # set up exp object without actually saving logs
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    exp = Experiment(debug=debug, save_dir=root_dir, name='tests_tt_dir', version=version)
+    return exp
+
+
+def init_save_dir():
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    save_dir = os.path.join(root_dir, 'save_dir')
+
+    if os.path.exists(save_dir):
+        shutil.rmtree(save_dir)
+
+    os.makedirs(save_dir, exist_ok=True)
+
+    return save_dir
+
+
+def clear_save_dir():
+    root_dir = os.path.dirname(os.path.realpath(__file__))
+    save_dir = os.path.join(root_dir, 'save_dir')
+    if os.path.exists(save_dir):
+        shutil.rmtree(save_dir)
+
+
+def load_model(exp, save_dir, on_gpu, map_location=None):
+
+    # load trained model
+    tags_path = exp.get_data_path(exp.name, exp.version)
+    tags_path = os.path.join(tags_path, 'meta_tags.csv')
+
+    checkpoints = [x for x in os.listdir(save_dir) if '.ckpt' in x]
+    weights_dir = os.path.join(save_dir, checkpoints[0])
+
+    trained_model = LightningTemplateModel.load_from_metrics(weights_path=weights_dir,
+                                                             tags_csv=tags_path,
+                                                             on_gpu=on_gpu,
+                                                             map_location=map_location)
+
+    assert trained_model is not None, 'loading model failed'
+
+    return trained_model
+
+
+def run_prediction(dataloader, trained_model):
+    # run prediction on 1 batch
+    for batch in dataloader:
+        break
+
+    x, y = batch
+    x = x.view(x.size(0), -1)
+
+    y_hat = trained_model(x)
+
+    # acc
+    labels_hat = torch.argmax(y_hat, dim=1)
+    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)
+    val_acc = torch.tensor(val_acc)
+    val_acc = val_acc.item()
+
+    print(val_acc)
+
+    assert val_acc > 0.50, 'this model is expected to get > 0.50 in test set (it got %f)' % val_acc
+
+
+def assert_ok_acc(trainer):
+    # this model should get 0.80+ acc
+    acc = trainer.tng_tqdm_dic['val_acc']
+    assert acc > 0.50, 'model failed to get expected 0.50 validation accuracy. Got: %f' % acc
+
+
+if __name__ == '__main__':
+    pytest.main([__file__])

tox.ini

@@ -0,0 +1,47 @@
+# this file is *not* meant to cover or endorse the use of tox or pytest or testing in general,
+#
+#  It's meant to show the use of:
+#
+#  - check-manifest
+#     confirm items checked into vcs are in your segdist
+#  - python setup.py check 
+#     confirm required package meta-data in setup.py
+#  - readme_renderer (when using a ReStructuredText README)
+#     confirms your long_description will render correctly on PyPI.
+#
+#  and also to help confirm pull requests to this project.
+
+[tox]
+envlist = py{35,36,37}
+
+[pytest]
+log_cli = 0
+log_cli_level = CRITICAL
+log_cli_format = %(message)s
+log_file = pytest.log
+log_file_level = DEBUG
+log_file_format = %(asctime)s [%(levelname)8s] %(message)s (%(filename)s:%(lineno)s)
+log_file_date_format=%Y-%m-%d %H:%M:%S
+
+[testenv]
+basepython =
+    py35: python3.5
+    py36: python3.6
+    py37: python3.7
+deps =
+    -r requirements.txt
+    -r ./tests/requirements.txt
+commands =
+    check-manifest --ignore tox.ini
+    python setup.py check -m -s
+    coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
+    flake8 .
+
+[flake8]
+exclude = .tox,*.egg,build,temp
+select = E,W,F
+doctests = True
+verbose = 2
+# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
+format = pylint
+max-line-length = 100

update.sh

@@ -11,10 +11,7 @@ rm -rf ./dist/*
 python3 setup.py sdist
 twine upload dist/*
 
-
-
 # to update docs
 # cd to root dir
 # mkdocs gh-deploy
 
-