release v0.3.6.3

Loading

.gitignore

@@ -9,6 +9,7 @@ model_weights/
 app/models/
 pip-wheel-metadata/
 test_tube_exp/
+tests/tests_tt_dir/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -119,4 +120,4 @@ 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/doc_requirements.txt

.travis.yml

@@ -0,0 +1,16 @@
+language: python
+python:
+  - "3.7"
+# command to install dependencies
+cache: pip
+install:
+  - pip install -e .
+  - pip install -r requirements.txt
+  - pip install -U numpy
+
+# keep build from timing out
+dist: xenial
+
+# command to run tests
+script:
+  - py.test # or py.test for Python versions 3.5 and below

README.md

@@ -9,31 +9,103 @@
 <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://pepy.tech/project/pytorch-lightning"><img src="https://pepy.tech/badge/pytorch-lightning" alt="PyPI version" height="18"></a>
+  <a href="https://github.com/williamFalcon/pytorch-lightning/tree/master/tests"><img src="https://github.com/williamFalcon/pytorch-lightning/blob/master/coverage.svg"></a>
+  <a href="https://travis-ci.org/williamFalcon/pytorch-lightning"><img src="https://travis-ci.org/williamFalcon/pytorch-lightning.svg?branch=master"></a>
+  <a href="https://williamfalcon.github.io/pytorch-lightning/"><img src="https://readthedocs.org/projects/pytorch-lightning/badge/?version=latest"></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>   
 
 ```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 defers training and validation loop logic to you. It guarantees correct, modern best practices for the core training logic.
 
 
 ## 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, model loading/saving, distributed training, 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: Data and training, validation loop logic. Don't worry about multiple gpus or speeding up your code, lightning will do that for you!
+
+## 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 pytorch_lightning as ptl
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+
+class CoolModel(ptl.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)]
+
+    @ptl.data_loader
+    def tng_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=True), batch_size=32)
+
+    @ptl.data_loader
+    def val_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+
+    @ptl.data_loader
+    def test_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+```
+
+2. Fit with a [trainer](https://williamfalcon.github.io/pytorch-lightning/Trainer/)    
+```python
+from pytorch_lightning import Trainer
+from test_tube import Experiment
+
+model = CoolModel()
+
+# fit on 32 gpus across 4 nodes
+exp = Experiment(save_dir='some/dir')
+trainer = Trainer(experiment=exp, nb_gpu_nodes=4, gpus=[0,1,2,3,4,5,6,7])
+
+trainer.fit(model)
+
+# see all experiment metrics here
+# tensorboard --log_dir some/dir   
+```
+
 
 ## What does lightning control for me?
 Everything!    
@@ -148,7 +220,7 @@ 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    
 
@@ -215,19 +287,22 @@ pip install pytorch-lightning
 
 # clone lightning for the demo
 git clone https://github.com/williamFalcon/pytorch-lightning.git
-cd examples/new_project_templates/
+cd pytorch_lightning/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.
+## 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
+```

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>

docs/LightningModule/RequiredTrainerInterface.md

@@ -3,7 +3,7 @@
 
 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 [this template](../../pytorch_lightning/examples/new_project_templates/lightning_module_template.py) and modify accordingly. 
 
 Otherwise, to Define a Lightning Module, implement the following methods:
 
@@ -26,6 +26,58 @@ Otherwise, to Define a Lightning Module, implement the following methods:
 - [update_tng_log_metrics](RequiredTrainerInterface.md#update_tng_log_metrics)
 - [add_model_specific_args](RequiredTrainerInterface.md#add_model_specific_args)
 
+---
+**Minimal example**
+```python
+import pytorch_lightning as ptl
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+
+class CoolModel(ptl.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)]
+
+    @ptl.data_loader
+    def tng_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=True), batch_size=32)
+
+    @ptl.data_loader
+    def val_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+
+    @ptl.data_loader
+    def test_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+```
+
 ---
 
 ### training_step
@@ -237,10 +289,10 @@ def load_model_specific(self, checkpoint):
 ### tng_dataloader 
 
 ``` {.python}
-@property
+@ptl.data_loader
 def tng_dataloader(self)
 ```
-Called by lightning during training loop. Define it as a property.
+Called by lightning during training loop. Make sure to use the @ptl.data_loader decorator, this ensures not calling this function until the data are needed.
 
 ##### Return
 Pytorch DataLoader
@@ -248,32 +300,26 @@ Pytorch DataLoader
 **Example**
 
 ``` {.python}
-@property
+@ptl.data_loader
 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
+    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
 ```
 
 --- 
 ### val_dataloader 
 
 ``` {.python}
-@property
+@ptl.data_loader
 def tng_dataloader(self)
 ```
-Called by lightning during validation loop. Define it as a property.
+Called by lightning during validation loop. Make sure to use the @ptl.data_loader decorator, this ensures not calling this function until the data are needed.
 
 ##### Return
 Pytorch DataLoader
@@ -281,32 +327,27 @@ Pytorch DataLoader
 **Example**
 
 ``` {.python}
-@property
+@ptl.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
 ```
 
 --- 
 ### test_dataloader 
 
 ``` {.python}
-@property
+@ptl.data_loader
 def test_dataloader(self)
 ```
-Called by lightning during test loop. Define it as a property.
+Called by lightning during test loop. Make sure to use the @ptl.data_loader decorator, this ensures not calling this function until the data are needed.
 
 ##### Return
 Pytorch DataLoader
@@ -314,22 +355,17 @@ Pytorch DataLoader
 **Example**
 
 ``` {.python}
-@property
+@ptl.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
 ```
 
 --- 

docs/Trainer/Distributed training.md

@@ -3,6 +3,26 @@ 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).   
+
 ---
 #### 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.    
@@ -37,16 +57,69 @@ 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"
+# lightning sets these flags for you automatically
+# no need to set yourself
+# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+# os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2,3,4,5,6,7"
 
-# DEFAULT
-trainer = Trainer(gpus=[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')
+
+# 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(f'export MASTER_PORT={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/doc_requirements.txt

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

docs/index.md

@@ -1,10 +1,11 @@
 ###### New project Quick Start    
 To start a new project define these two files.   
 
-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)
+1. [Define a LightningModule](/pytorch-lightning/LightningModule/RequiredTrainerInterface/) 
+2. [Define a trainer](https://williamfalcon.github.io/pytorch-lightning/Trainer/)
+    - [Basic CPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/examples/new_project_templates/single_cpu_template.py) 
+    - [Multi-GPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/examples/new_project_templates/single_gpu_node_template.py)
+    - [GPU cluster Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/pytorch_lightning/examples/new_project_templates/multi_node_cluster_template.py)
 
 ###### Docs shortcuts
 - [LightningModule](LightningModule/RequiredTrainerInterface/)  

examples/new_project_templates/__init__.py

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

pytorch_lightning/__init__.py

@@ -1,2 +1,3 @@
 from .models import Trainer
-from .root_module.root_module import LightningModule
+from .root_module.root_module import LightningModule
+from .root_module.decorators import data_loader

pytorch_lightning/examples/__init__.py

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

pytorch_lightning/examples/new_project_templates/lightning_module_template.py

@@ -10,6 +10,7 @@ from torch import optim
 from torch.utils.data import DataLoader
 from torch.utils.data.distributed import DistributedSampler
 
+import pytorch_lightning as ptl
 from pytorch_lightning.root_module.root_module import LightningModule
 
 
@@ -24,10 +25,14 @@ 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()
 
@@ -78,11 +83,16 @@ 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
         })
@@ -105,10 +115,19 @@ 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).cuda(loss_val.device.index),
+            'val_acc': val_acc,
         })
 
         # can also return just a scalar instead of a dict (return loss_val)
@@ -135,20 +154,6 @@ class LightningTemplateModel(LightningModule):
         tqdm_dic = {'val_loss': val_loss_mean.item(), 'val_acc': val_acc_mean.item()}
         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
     # ---------------------
@@ -186,38 +191,23 @@ class LightningTemplateModel(LightningModule):
 
         return loader
 
-    @property
+    @ptl.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
+    @ptl.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)
 
-    @property
+    @ptl.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:

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/models/trainer.py

@@ -1,12 +1,12 @@
 """
 The trainer handles all the logic for running a val loop, training loop, distributing, etc...
 """
-from time import sleep
 import subprocess
 import traceback
 import warnings
 import os
 import pdb
+import re
 
 import torch
 from torch.utils.data.distributed import DistributedSampler
@@ -19,12 +19,12 @@ import tqdm
 from pytorch_lightning.root_module.memory import get_gpu_memory_map
 from pytorch_lightning.root_module.model_saving import TrainerIO
 from pytorch_lightning.pt_overrides.override_data_parallel import LightningDistributedDataParallel, LightningDataParallel
-
+from pytorch_lightning.utils.debugging import MisconfigurationException
 
 try:
     from apex import amp
     APEX_AVAILABLE = True
-except ModuleNotFoundError:
+except ModuleNotFoundError: # pragma: no cover
     APEX_AVAILABLE = False
 
 
@@ -114,6 +114,7 @@ class Trainer(TrainerIO):
         """
 
         # Transfer params
+
         self.nb_gpu_nodes = nb_gpu_nodes
         self.gradient_clip = gradient_clip
         self.check_val_every_n_epoch = check_val_every_n_epoch
@@ -146,17 +147,33 @@ class Trainer(TrainerIO):
         self.print_nan_grads = print_nan_grads
         self.data_parallel_device_ids = None
         self.world_size = 1
+        self.node_rank = 0
         self.use_ddp = False
         self.use_dp = False
 
+        # training bookeeping
+        self.total_batch_nb = 0
+        self.running_loss = []
+        self.avg_loss = 0
+        self.batch_nb = 0
+        self.tqdm_metrics = {}
+        self.nb_val_batches = None
+        self.nb_tng_batches = None
+        self.nb_test_batches = None
+
         # gpus come in as a string.
         # if gpus = -1 then use all available devices
         # otherwise, split the string using commas
         if gpus is not None:
-            if gpus == '-1':
-                self.data_parallel_device_ids = list(range(0, torch.cuda.device_count()))
+            if type(gpus) is list:
+                self.data_parallel_device_ids = gpus
+            elif type(gpus) is str:
+                if gpus == '-1':
+                    self.data_parallel_device_ids = list(range(0, torch.cuda.device_count()))
+                else:
+                    self.data_parallel_device_ids = [int(x.strip()) for x in gpus.split(',')]
             else:
-                self.data_parallel_device_ids = [int(x.strip()) for x in gpus.split(',')]
+                raise Exception('gpus has to be a string or list of ids')
 
             # set the correct cuda visible devices (using pci order)
             os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
@@ -170,6 +187,28 @@ class Trainer(TrainerIO):
             self.use_dp = distributed_backend == 'dp'
             self.use_ddp = distributed_backend == 'ddp'
 
+            # use ddp automatically if nb_gpu_nodes > 1
+            if nb_gpu_nodes > 1 and self.use_dp:  # pragma: no cover
+                self.use_ddp = True
+                self.use_dp = False
+                w = 'DataParallel does not support nb_gpu_nodes > 1. ' \
+                    'Switching to DistributedDataParallel for you. ' \
+                    'To silence this warning set distributed_backend=ddp'
+                warnings.warn(w)
+
+        # extract SLURM flag vars
+        # whenever we have the correct number of tasks, we let slurm manage processes
+        # otherwise we launch the required number of processes
+        if self.use_ddp:
+            self.nb_requested_gpus = len(self.data_parallel_device_ids) * self.nb_gpu_nodes
+            self.nb_slurm_tasks = 0
+            try:
+                self.nb_slurm_tasks = int(os.environ['SLURM_NTASKS'])
+                self.is_slurm_managing_tasks = self.nb_slurm_tasks == self.nb_requested_gpus
+            except Exception as e:
+                # likely not on slurm, so set the slurm managed flag to false
+                self.is_slurm_managing_tasks = False
+
         # process info
         self.proc_rank = 0
 
@@ -199,7 +238,7 @@ class Trainer(TrainerIO):
         if self.use_amp:
             print('using 16bit precision')
 
-        if use_amp and not APEX_AVAILABLE:
+        if use_amp and not APEX_AVAILABLE:  # pragma: no cover
             msg = '''
             You set use_amp=True but do not have apex installed.
             Install apex first using this guide and rerun with use_amp=True: 
@@ -207,7 +246,7 @@ class Trainer(TrainerIO):
             
             this run will NOT use 16 bit precision
             '''
-            warnings.warn(msg)
+            raise ModuleNotFoundError(msg)
 
     @property
     def data_parallel(self):
@@ -235,6 +274,7 @@ class Trainer(TrainerIO):
 
     @property
     def __tng_tqdm_dic(self):
+        # ForkedPdb().set_trace()
         tqdm_dic = {
             'tng_loss': '{0:.3f}'.format(self.avg_loss),
             'v_nb': '{}'.format(self.experiment.version),
@@ -248,13 +288,15 @@ class Trainer(TrainerIO):
 
         return tqdm_dic
 
+    @property
+    def tng_tqdm_dic(self):
+        """
+        Read-only for tqdm metrics
+        :return:
+        """
+        return self.__tng_tqdm_dic
+
     def __layout_bookeeping(self):
-        # training bookeeping
-        self.total_batch_nb = 0
-        self.running_loss = []
-        self.avg_loss = 0
-        self.batch_nb = 0
-        self.tqdm_metrics = {}
 
         # determine number of training batches
         self.nb_tng_batches = len(self.tng_dataloader)
@@ -301,7 +343,7 @@ class Trainer(TrainerIO):
         # run training
         for batch_i, data_batch in enumerate(dataloader):
 
-            if data_batch is None:
+            if data_batch is None:  # pragma: no cover
                 continue
 
             # stop short when on fast dev run
@@ -340,7 +382,7 @@ class Trainer(TrainerIO):
 
         return val_results
 
-    def __get_dataloaders(self, model):
+    def get_dataloaders(self, model):
         """
         Dataloaders are provided by the model
         :param model:
@@ -363,7 +405,7 @@ class Trainer(TrainerIO):
             dist_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
             dataloader = Dataloader(dataset, sampler=dist_sampler)
             '''
-            raise Exception(msg)
+            raise MisconfigurationException(msg)
 
     # -----------------------------
     # MODEL TRAINING
@@ -375,24 +417,14 @@ class Trainer(TrainerIO):
             # must copy only the meta of the exp so it survives pickle/unpickle when going to new process
             self.experiment = self.experiment.get_meta_copy()
 
-            # whenever we have the correct number of tasks, we let slurm manage processes
-            # otherwise we launch the required number of processes
-            try:
-                nb_slurm_tasks = int(os.environ['SLURM_NTASKS'])
-                nb_requested_gpus = len(self.data_parallel_device_ids)
-                is_slurm_managing_tasks = nb_slurm_tasks == nb_requested_gpus
-            except Exception as e:
-                # likely not on slurm, so set the slurm managed flag to false
-                is_slurm_managing_tasks = False
-
-            if is_slurm_managing_tasks:
+            if self.is_slurm_managing_tasks:
                 task = int(os.environ['SLURM_LOCALID'])
                 self.ddp_train(task, model)
             else:
                 msg = f"""
-                You requested {nb_requested_gpus} GPUs but launched {nb_slurm_tasks} slurm tasks. 
-                We will launch {nb_requested_gpus} processes for you. 
-                We recommend you let slurm manage the processes by setting: --ntasks-per-node={nb_requested_gpus}
+                You requested {self.nb_requested_gpus} GPUs but launched {self.nb_slurm_tasks} slurm tasks. 
+                We will launch {self.nb_requested_gpus} processes for you. 
+                We recommend you let slurm manage the processes by setting: --ntasks-per-node={self.nb_requested_gpus}
                 If you're not using SLURM, ignore this message!
                 """
                 warnings.warn(msg)
@@ -401,40 +433,41 @@ class Trainer(TrainerIO):
         # 1 gpu or dp option triggers training using DP module
         # easier to avoid NCCL issues
         elif self.use_dp:
-            self.dp_train(model)
+            self.__dp_train(model)
 
         # ON CPU
         else:
+            # run through amp wrapper
+            if self.use_amp:
+                raise MisconfigurationException('amp + cpu is not supported. Please use a GPU option')
+
             # CHOOSE OPTIMIZER
             # filter out the weights that were done on gpu so we can load on good old cpus
             self.optimizers = model.configure_optimizers()
 
-            # run through amp wrapper
-            if self.use_amp:
-                # An example
-                model, optimizers = amp.initialize(
-                    model, self.optimizers, opt_level=self.amp_level,
-                )
-                self.optimizers = optimizers
-
             self.__run_pretrain_routine(model)
 
-    def dp_train(self, model):
+        # return 1 when finished
+        # used for testing or when we need to know that training succeeded
+        return 1
+
+    def __dp_train(self, model):
 
         # CHOOSE OPTIMIZER
         # filter out the weights that were done on gpu so we can load on good old cpus
         self.optimizers = model.configure_optimizers()
 
         model.cuda(self.data_parallel_device_ids[0])
-        model = LightningDataParallel(model, device_ids=self.data_parallel_device_ids)
 
-        # run through amp wrapper
-        if self.use_amp:
-            # An example
-            model, optimizers = amp.initialize(
-                model, self.optimizers, opt_level=self.amp_level,
-            )
-            self.optimizers = optimizers
+        # check for this bug (amp + dp + !01 doesn't work)
+        # https://github.com/NVIDIA/apex/issues/227
+        if self.use_dp and self.use_amp:
+            m = f'amp level {self.amp_level} with DataParallel is not supported. ' \
+                f'See this note from NVIDIA for more info: https://github.com/NVIDIA/apex/issues/227. ' \
+                f'We recommend you switch to ddp if you want to use amp'
+            raise MisconfigurationException(m)
+
+        model = LightningDataParallel(model, device_ids=self.data_parallel_device_ids)
 
         self.__run_pretrain_routine(model)
 
@@ -449,9 +482,10 @@ class Trainer(TrainerIO):
         # node rank using relative slurm id
         # otherwise default to node rank 0
         try:
-            node_rank = int(os.environ['SLURM_NODEID'])
-        except KeyError as e:
-            node_rank = 0
+            node_id = os.environ['SLURM_NODEID']
+            self.node_rank = int(node_id)
+        except Exception as e:
+            self.node_rank = 0
 
         # recover original exp before went into process
         # init in write mode only on proc 0
@@ -459,12 +493,15 @@ class Trainer(TrainerIO):
         self.experiment = self.experiment.get_non_ddp_exp()
 
         # show progbar only on prog_rank 0
-        self.prog_bar = self.prog_bar and node_rank == 0 and gpu_nb == 0
+        self.prog_bar = self.prog_bar and self.node_rank == 0 and gpu_nb == 0
 
         # determine which process we are and world size
-        self.proc_rank = node_rank * len(self.data_parallel_device_ids) + gpu_nb
+        self.proc_rank = self.node_rank * len(self.data_parallel_device_ids) + gpu_nb
         self.world_size = self.nb_gpu_nodes * len(self.data_parallel_device_ids)
 
+        # let the exp know the rank to avoid overwriting logs
+        self.experiment.rank = self.proc_rank
+
         # set up server using proc 0's ip address
         # try to init for 20 times at max in case ports are taken
         # where to store ip_table
@@ -488,7 +525,7 @@ class Trainer(TrainerIO):
             )
             self.optimizers = optimizers
 
-        model = LightningDistributedDataParallel(model, device_ids=[gpu_nb])
+        model = LightningDistributedDataParallel(model, device_ids=[gpu_nb], find_unused_parameters=True)
 
         # continue training routine
         self.__run_pretrain_routine(model)
@@ -501,22 +538,36 @@ class Trainer(TrainerIO):
         :param tries:
         :return:
         """
+        # sets the appropriate port
         try:
             port = os.environ['MASTER_PORT']
         except Exception as e:
             port = 12910
             os.environ['MASTER_PORT'] = f'{port}'
 
+        # figure out the root node addr
         try:
             root_node = os.environ['SLURM_NODELIST'].split(' ')[0]
         except Exception as e:
             root_node = '127.0.0.2'
 
+        root_node = self.resolve_root_node_address(root_node)
         os.environ['MASTER_ADDR'] = root_node
 
-        sleep(self.proc_rank*0.5)
         dist.init_process_group("nccl", rank=self.proc_rank, world_size=self.world_size)
 
+    def resolve_root_node_address(self, root_node):
+        if '[' in root_node:
+            name = root_node.split('[')[0]
+            number = root_node.split(',')[0]
+            if '-' in number:
+                number = number.split('-')[0]
+
+            number = re.sub('[^0-9]', '', number)
+            root_node = name + number
+
+        return root_node
+
     def __run_pretrain_routine(self, model):
         """
         Sanity check a few things before starting actual training
@@ -533,7 +584,7 @@ class Trainer(TrainerIO):
         ref_model.on_gpu = self.on_gpu
 
         # transfer data loaders from model
-        self.__get_dataloaders(ref_model)
+        self.get_dataloaders(ref_model)
 
         # init training constants
         self.__layout_bookeeping()
@@ -559,14 +610,18 @@ class Trainer(TrainerIO):
         if self.proc_rank == 0:
             self.experiment.save()
 
+        # track model now.
+        # if cluster resets state, the model will update with the saved weights
+        self.model = model
+
         # enable cluster checkpointing
-        if self.cluster is not None:
+        # also restores training state
+        if self.cluster is not None:  # pragma: no cover
             self.enable_auto_hpc_walltime_manager()
 
         # ---------------------------
         # CORE TRAINING LOOP
         # ---------------------------
-        self.model = model
         self.__train()
 
     def __train(self):
@@ -629,7 +684,7 @@ class Trainer(TrainerIO):
                     # nb_params, nb_tensors = count_mem_items()
 
                     model = self.__get_model()
-                    metrics = model.update_tng_log_metrics(self.__tng_tqdm_dic)
+                    metrics = self.__tng_tqdm_dic
 
                     # add gpu memory
                     if self.on_gpu:
@@ -743,6 +798,11 @@ class Trainer(TrainerIO):
         else:
             loss.backward()
 
+        # insert after step hook
+        if self.__is_function_implemented('on_after_backward'):
+            model_ref = self.__get_model()
+            response = model_ref.on_after_backward()
+
         if self.print_nan_grads:
             model = self.__get_model()
             for param in model.parameters():
@@ -763,6 +823,11 @@ class Trainer(TrainerIO):
             for optimizer in self.optimizers:
                 optimizer.step()
 
+                # insert after step hook
+                if self.__is_function_implemented('on_before_zero_grad'):
+                    model_ref = self.__get_model()
+                    response = model_ref.on_before_zero_grad(optimizer)
+
                 # clear gradients
                 optimizer.zero_grad()
 
@@ -795,30 +860,25 @@ class Trainer(TrainerIO):
         elif not can_check_epoch:
             return
 
-        try:
-            # hook
-            if self.__is_function_implemented('on_pre_performance_check'):
-                model = self.__get_model()
-                model.on_pre_performance_check()
+        # hook
+        if self.__is_function_implemented('on_pre_performance_check'):
+            model = self.__get_model()
+            model.on_pre_performance_check()
 
-            # use full val set on end of epoch
-            # use a small portion otherwise
-            max_batches = None if not self.fast_dev_run else 1
-            model_specific_tqdm_metrics_dic = self.validate(
-                self.model,
-                self.val_dataloader,
-                max_batches
-            )
-            self.__add_tqdm_metrics(model_specific_tqdm_metrics_dic)
+        # use full val set on end of epoch
+        # use a small portion otherwise
+        max_batches = None if not self.fast_dev_run else 1
+        model_specific_tqdm_metrics_dic = self.validate(
+            self.model,
+            self.val_dataloader,
+            max_batches
+        )
+        self.__add_tqdm_metrics(model_specific_tqdm_metrics_dic)
 
-            # hook
-            if self.__is_function_implemented('on_post_performance_check'):
-                model = self.__get_model()
-                model.on_post_performance_check()
-
-        except Exception as e:
-            print(e)
-            print(traceback.print_exc())
+        # hook
+        if self.__is_function_implemented('on_post_performance_check'):
+            model = self.__get_model()
+            model.on_post_performance_check()
 
         if self.progress_bar:
             # add model specific metrics
@@ -826,6 +886,6 @@ class Trainer(TrainerIO):
             self.prog_bar.set_postfix(**tqdm_metrics)
 
         # model checkpointing
-        if self.proc_rank == 0 and self.checkpoint_callback:
+        if self.proc_rank == 0 and self.checkpoint_callback is not None:
             print('save callback...')
             self.checkpoint_callback.on_epoch_end(epoch=self.current_epoch, logs=self.__tng_tqdm_dic)

pytorch_lightning/pt_overrides/override_data_parallel.py

@@ -9,7 +9,7 @@ from torch.cuda._utils import _get_device_index
 import pdb
 
 
-def _find_tensors(obj):
+def _find_tensors(obj):  # pragma: no cover
     r"""
     Recursively find all tensors contained in the specified object.
     """
@@ -22,8 +22,7 @@ def _find_tensors(obj):
     return []
 
 
-
-def get_a_var(obj):
+def get_a_var(obj):  # pragma: no cover
     if isinstance(obj, torch.Tensor):
         return obj
 
@@ -78,7 +77,7 @@ class LightningDistributedDataParallel(DistributedDataParallel):
     def parallel_apply(self, replicas, inputs, kwargs):
         return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
 
-    def forward(self, *inputs, **kwargs):
+    def forward(self, *inputs, **kwargs):  # pragma: no cover
         self._sync_params()
         if self.device_ids:
             inputs, kwargs = self.scatter(inputs, kwargs, self.device_ids)
@@ -113,7 +112,7 @@ class LightningDistributedDataParallel(DistributedDataParallel):
         return output
 
 
-def parallel_apply(modules, inputs, kwargs_tup=None, devices=None):
+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`.

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

@@ -27,14 +27,3 @@ class GradInformation(nn.Module):
         results['grad_{}_norm_total'.format(norm_type)] = round(total_norm.data.cpu().numpy().flatten()[0], 3)
         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

@@ -22,3 +22,24 @@ class ModelHooks(torch.nn.Module):
     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

@@ -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
@@ -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
 
@@ -128,10 +146,13 @@ 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)):
@@ -140,7 +161,7 @@ def print_mem_stack():
             pass
 
 
-def count_mem_items():
+def count_mem_items(): # pragma: no cover
     nb_params = 0
     nb_tensors = 0
     for obj in gc.get_objects():

pytorch_lightning/root_module/model_saving.py

@@ -4,34 +4,36 @@ import re
 import pdb
 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
-        :return:
+        Give the model a chance to add something to the checkpoint.
+        state_dict is already there
         """
-        raise NotImplementedError
+        pass
 
     # -------------------------
     # OPTIONAL HOOKS
     # -------------------------
-    def on_hpc_save(self):
+    def on_hpc_save(self, checkpoint):
         """
         Hook to do whatever you need right before Slurm manager saves the model
         :return:
         """
         pass
 
-    def on_hpc_load(self):
+    def on_hpc_load(self, checkpoint):
         """
         Hook to do whatever you need right before Slurm manager loads the model
         :return:
@@ -41,6 +43,11 @@ class ModelIO(object):
 
 class TrainerIO(object):
 
+    def __get_model(self):
+        is_dp_module = type(self.model) is LightningDistributedDataParallel or type(self.model) is LightningDataParallel
+        model = self.model.module if is_dp_module else self.model
+        return model
+
     # --------------------
     # MODEL SAVE CHECKPOINT
     # --------------------
@@ -51,27 +58,32 @@ class TrainerIO(object):
         torch.save(checkpoint, filepath)
 
     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
+
         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
-        is_dp_module = type(self.model) is LightningDistributedDataParallel or type(self.model) is LightningDataParallel
-        model = self.model.module if is_dp_module else self.model
-        checkpoint_dict = model.get_save_dict()
+        # 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
 
     # --------------------
@@ -104,9 +116,13 @@ 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']
 
@@ -135,13 +151,15 @@ class TrainerIO(object):
         filepath = '{}/hpc_ckpt_{}.ckpt'.format(folderpath, ckpt_number)
 
         # give model a chance to do something on hpc_save
-        self.on_hpc_save()
+        model = self.__get_model()
+        checkpoint = self.dump_checkpoint()
 
-        # request what to save from the model
-        checkpoint_dict = 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))
@@ -151,15 +169,17 @@ 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()
+
+        # load the state_dict on the model automatically
+        model.load_state_dict(checkpoint['state_dict'])
 
         # call model hook
-        self.on_hpc_load()
+        model.on_hpc_load(checkpoint)
 
     def max_ckpt_in_folder(self, path):
         files = os.listdir(path)

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

@@ -1,19 +1,15 @@
-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, OptimizerConfig, ModelHooks):
+class LightningModule(GradInformation, ModelIO, 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
@@ -22,15 +18,11 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         self.loaded_optimizer_states_dict = {}
         self.trainer = None
         self.experiment = None
+        self.example_input_array = None
 
         # track if gpu was requested for checkpointing
         self.on_gpu = False
 
-        # computed vars for the dataloaders
-        self._tng_dataloader = None
-        self._val_dataloader = None
-        self._test_dataloader = None
-
     def forward(self, *args, **kwargs):
         """
         Expand model in into whatever you need.
@@ -71,37 +63,7 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         """
         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:
-        """
-        return logs
-
-    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 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
@@ -109,7 +71,7 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         """
         raise NotImplementedError
 
-    @property
+    @data_loader
     def test_dataloader(self):
         """
         Implement a function to load an h5py of this data
@@ -117,7 +79,7 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         """
         raise NotImplementedError
 
-    @property
+    @data_loader
     def val_dataloader(self):
         """
         Implement a function to load an h5py of this data
@@ -125,16 +87,6 @@ class LightningModule(GradInformation, ModelIO, OptimizerConfig, ModelHooks):
         """
         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
-
     @classmethod
     def load_from_metrics(cls, weights_path, tags_csv, on_gpu, map_location=None):
         """
@@ -156,9 +108,26 @@ 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_models/lm_test_module.py

@@ -0,0 +1,253 @@
+import os
+from collections import OrderedDict
+import torch.nn as nn
+from torchvision.datasets import MNIST
+import torchvision.transforms as transforms
+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
+
+from pytorch_lightning.root_module.root_module import LightningModule
+import pytorch_lightning as ptl
+
+
+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)
+
+        output = OrderedDict({
+            '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):
+        """
+        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 self.trainer.batch_nb % 1 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+            })
+            return output
+        if self.trainer.batch_nb % 2 == 0:
+            return val_acc
+
+        if self.trainer.batch_nb % 3 == 0:
+            output = OrderedDict({
+                'val_loss': loss_val,
+                'val_acc': val_acc,
+                'test_dic': {'val_loss_a': loss_val}
+            })
+            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
+        """
+        optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
+        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 as e:
+            pass
+
+        should_shuffle = train_sampler is None
+        loader = DataLoader(
+            dataset=dataset,
+            batch_size=batch_size,
+            shuffle=should_shuffle,
+            sampler=train_sampler
+        )
+
+        return loader
+
+    @ptl.data_loader
+    def tng_dataloader(self):
+        return self.__dataloader(train=True)
+
+    @ptl.data_loader
+    def val_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @ptl.data_loader
+    def test_dataloader(self):
+        return self.__dataloader(train=False)
+
+    @staticmethod
+    def add_model_specific_args(parent_parser, root_dir):
+        """
+        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)
+        parser.add_argument('--hidden_dim', default=50000, type=int) # 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*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 the gpus being used across all nodes')
+        return parser

pytorch_lightning/trainer_main.py

@@ -52,10 +52,6 @@ def main(hparams, cluster, results_dict):
     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,

pytorch_lightning/utils/debugging.py

@@ -0,0 +1,5 @@
+import pdb
+import sys
+
+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 @@
-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`.
-    """
-    from matplotlib import pyplot as plt
-    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 +1,9 @@
-
-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
+coverage==4.5.3
+mkdocs==1.0.4
+pytest==5.0.1
 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

setup.cfg

@@ -16,6 +16,33 @@ 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
+    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
+
 [flake8]
 ignore = E731,W504,F401,F841
 max-line-length = 120

setup.py

@@ -7,7 +7,7 @@ from setuptools import setup, find_packages
 # http://blog.ionelmc.ro/2014/05/25/python-packaging/
 setup(
     name="pytorch-lightning",
-    version='0.2.5.2',
+    version='0.3.6.3',
     description="The Keras for ML researchers using PyTorch",
     author="William Falcon",
     author_email="waf2107@columbia.edu",
@@ -19,7 +19,7 @@ setup(
     install_requires=[
         "torch>=1.1.0",
         "tqdm",
-        "test-tube>=0.6.7.1",
+        "test-tube>=0.6.7.4",
     ],
     packages=find_packages(),
     long_description=open("README.md", encoding="utf-8").read(),

tests/README.md

@@ -0,0 +1,58 @@
+# 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
+```
+
+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   
+
+```bash
+cd pytorch-lightning
+
+# generate coverage 
+pip install coverage
+coverage run tests/test_models.py   
+
+# print coverage stats
+coverage report -m   
+```
+
+

tests/debug.py

@@ -0,0 +1,180 @@
+import pytest
+from pytorch_lightning import Trainer
+from pytorch_lightning.examples.new_project_templates.lightning_module_template import LightningTemplateModel
+from argparse import Namespace
+from test_tube import Experiment
+from pytorch_lightning.callbacks import ModelCheckpoint
+import numpy as np
+import warnings
+import torch
+import os
+import shutil
+import pdb
+
+import pytorch_lightning as ptl
+import torch
+from torch.nn import functional as F
+from torch.utils.data import DataLoader
+from torchvision.datasets import MNIST
+
+
+class CoolModel(ptl.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)]
+
+    @ptl.data_loader
+    def tng_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=True), batch_size=32)
+
+    @ptl.data_loader
+    def val_dataloader(self):
+        return DataLoader(MNIST('path/to/save', train=False), batch_size=32)
+
+    @ptl.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, f'this model is expected to get > 0.7 in test set (it got {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/test_models.py

@@ -0,0 +1,688 @@
+import pytest
+from pytorch_lightning import Trainer
+from pytorch_lightning.examples.new_project_templates.lightning_module_template import LightningTemplateModel
+from pytorch_lightning.testing_models.lm_test_module import LightningTestModel
+from argparse import Namespace
+from test_tube import Experiment, SlurmCluster
+from pytorch_lightning.callbacks import ModelCheckpoint, EarlyStopping
+from pytorch_lightning.utils.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
+import numpy as np
+import warnings
+import torch
+import os
+import shutil
+import pdb
+
+SEED = 2334
+torch.manual_seed(SEED)
+np.random.seed(SEED)
+
+
+# ------------------------------------------------------------------------
+# TESTS
+# ------------------------------------------------------------------------
+
+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_dir = init_save_dir()
+
+    # 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 = 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_early_stopping_cpu_model():
+    """
+    Test each of the trainer options
+    :return:
+    """
+
+    stopping = EarlyStopping()
+    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_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(),
+        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_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_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.raises(MisconfigurationException):
+        trainer.get_dataloaders(model)
+
+    clear_save_dir()
+
+
+# ------------------------------------------------------------------------
+# 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 = 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():
+    # set up model with these hyperparams
+    hparams = get_hparams()
+    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, 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, f'this model is expected to get > 0.50 in test set (it got {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, f'model failed to get expected 0.50 validation accuracy. Got: {acc}'
+
+
+if __name__ == '__main__':
+    pytest.main([__file__])