release v0.5.1.2

README.md

@@ -265,24 +265,8 @@ Lightning also adds a text column with all the hyperparameters for this experime
 
 ![tensorboard-support](./docs/source/_static/tf_tags.png)
 
-Simply note the path you set for the [Experiment](https://williamfalcon.github.io/test-tube/experiment_tracking/experiment/) from [test_tube](https://github.com/williamFalcon/test-tube)
-```python
-from test_tube import Experiment
-from pytorch_lightning import Trainer
-
-exp = Experiment(save_dir='/some/path')
-trainer = Trainer(experiment=exp)
-...
-```   
-
-And run tensorboard from that dir   
-```bash
-tensorboard --logdir /some/path     
-```    
-
 ## Lightning automates all of the following ([each is also configurable](https://williamfalcon.github.io/pytorch-lightning/Trainer/)):
 
-
 #### Checkpointing    
 
 - [Checkpoint callback](https://williamfalcon.github.io/pytorch-lightning/Trainer/Checkpointing/#model-saving)

docs/LightningModule/RequiredTrainerInterface.md

@@ -77,7 +77,7 @@ class CoolModel(pl.LightningModule):
 
     def configure_optimizers(self):
         # REQUIRED
-        return [torch.optim.Adam(self.parameters(), lr=0.02)]
+        return torch.optim.Adam(self.parameters(), lr=0.02)
 
     @pl.data_loader
     def train_dataloader(self):

docs/Trainer/hooks.md

@@ -65,12 +65,12 @@ You can override this method to adjust how you do the optimizer step for each op
 Called once per optimizer
 ```python
 # DEFAULT
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
     optimizer.step()   
     optimizer.zero_grad()   
     
 # Alternating schedule for optimizer steps (ie: GANs)    
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
     # update generator opt every 2 steps
     if optimizer_i == 0:
         if batch_nb % 2 == 0 :
@@ -91,7 +91,7 @@ This step allows you to do a lot of non-standard training tricks such as learnin
 
 ```python
 # learning rate warm-up
-def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i):
+def optimizer_step(self, current_epoch, batch_nb, optimizer, optimizer_i, second_order_closure=None):
     # warm up lr
     if self.trainer.global_step < 500:
         lr_scale = min(1., float(self.trainer.global_step + 1) / 500.)

docs/index.md

@@ -60,9 +60,8 @@ Notice a few things about this flow:
 ###### Templates 
 1. [MNIST LightningModule](https://williamfalcon.github.io/pytorch-lightning/LightningModule/RequiredTrainerInterface/#minimal-example) 
 2. [Trainer](https://williamfalcon.github.io/pytorch-lightning/Trainer/)
-    - [Basic CPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/single_cpu_template.py) 
-    - [Multi-GPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/single_gpu_node_template.py)
-    - [GPU cluster Trainer Template](https://github.com/williamFalcon/pytorch-lightning/blob/master/examples/new_project_templates/multi_node_cluster_template.py)
+    - [Basic CPU, GPU Trainer Template](https://github.com/williamFalcon/pytorch-lightning/tree/master/examples/basic_examples) 
+    - [GPU cluster Trainer Template](https://github.com/williamFalcon/pytorch-lightning/tree/master/examples/multi_node_examples)
 
 ###### Docs shortcuts
 - [LightningModule](LightningModule/RequiredTrainerInterface/)  

examples/multi_node_examples/README.md

@@ -1,6 +1,7 @@
 # Multi-node example   
 
-To run this demo which launches a single job that trains on 2 nodes (2 gpus per node), do the following:
+This demo launches a job using 2 GPUs on 2 different nodes (4 GPUs total).
+To run this demo do the following:
 
 1. Log into the jumphost node of your SLURM-managed cluster.  
 2. Create a conda environment with Lightning and a GPU PyTorch version.   

pytorch_lightning/logging/test_tube_logger.py

@@ -10,11 +10,13 @@ class TestTubeLogger(LightningLoggerBase):
     __test__ = False
 
     def __init__(
-        self, save_dir, name="default", debug=False, version=None, create_git_tag=False
+        self, save_dir, name="default", description=None, debug=False,
+            version=None, create_git_tag=False
     ):
         super().__init__()
         self.save_dir = save_dir
         self.name = name
+        self.description = description
         self.debug = debug
         self._version = version
         self.create_git_tag = create_git_tag
@@ -29,6 +31,7 @@ class TestTubeLogger(LightningLoggerBase):
             name=self.name,
             debug=self.debug,
             version=self.version,
+            description=self.description,
             create_git_tag=self.create_git_tag,
             rank=self.rank,
         )

pytorch_lightning/trainer/trainer.py

@@ -659,11 +659,12 @@ class Trainer(TrainerIO):
                 """
                 warnings.warn(msg)
 
-            if on_ddp and self.get_val_dataloaders is not None:
+            if on_ddp and self.get_val_dataloaders() is not None:
                 for dataloader in self.get_val_dataloaders():
                     if not isinstance(dataloader.sampler, DistributedSampler):
                         msg = """
                         Your val_dataloader(s) don't use DistributedSampler.
+
                         You're using multiple gpus and multiple nodes without using a
                         DistributedSampler to assign a subset of your data to each process.
                         To silence this warning, pass a DistributedSampler to your DataLoader.
@@ -682,11 +683,12 @@ class Trainer(TrainerIO):
                         warnings.warn(msg)
                         break
 
-            if on_ddp and self.get_test_dataloaders is not None:
+            if on_ddp and self.get_test_dataloaders() is not None:
                 for dataloader in self.get_test_dataloaders():
                     if not isinstance(dataloader.sampler, DistributedSampler):
                         msg = """
                         Your test_dataloader(s) don't use DistributedSampler.
+
                         You're using multiple gpus and multiple nodes without using a
                         DistributedSampler to assign a subset of your data to each process.
                         To silence this warning, pass a DistributedSampler to your DataLoader.

setup.py

@@ -14,7 +14,7 @@ from setuptools import setup, find_packages
 # engineer specific practices
 setup(
     name='pytorch-lightning',
-    version='0.5.1',
+    version='0.5.1.2',
     description='The Keras for ML researchers using PyTorch',
     author='William Falcon',
     author_email='waf2107@columbia.edu',

tests/test_models.py

@@ -446,7 +446,7 @@ def test_gradient_accumulation_scheduling():
         assert Trainer(accumulate_grad_batches={1: 2.5, 3: 5})
 
     # test optimizer call freq matches scheduler
-    def optimizer_step(self, epoch_nb, batch_nb, optimizer, optimizer_i):
+    def optimizer_step(self, epoch_nb, batch_nb, optimizer, optimizer_i, second_order_closure=None):
         # only test the first 12 batches in epoch
         if batch_nb < 12:
             if epoch_nb == 0: