Fixes print issues and data_loader (#1080)

* print issue

* print issue

* print issue

* print issue

* print issue

pytorch_lightning/__init__.py

@@ -27,10 +27,12 @@
     from .core import LightningModule
     from .trainer import Trainer
     from .callbacks import Callback
+    from .core import data_loader
 
     __all__ = [
         'Trainer',
         'LightningModule',
         'Callback',
+        'data_loader'
     ]
     # __call__ = __all__

pytorch_lightning/core/__init__.py

@@ -312,7 +312,8 @@ def test_dataloader(self):
 
 """
 
+from .decorators import data_loader
 from .lightning import LightningModule
 
-__all__ = ['LightningModule']
+__all__ = ['LightningModule', 'data_loader']
 # __call__ = __all__

pytorch_lightning/core/lightning.py

@@ -85,7 +85,7 @@ def forward(self, x):
 
         """
         if self.trainer.proc_rank == 0:
-            log.info(*args, **kwargs)
+            print(*args, **kwargs)
 
     @abstractmethod
     def forward(self, *args, **kwargs):
@@ -1189,9 +1189,6 @@ def test_dataloader(self):
         .. note:: If you don't need a test dataset and a test_step, you don't need to implement
             this method.
 
-        .. note:: If you want to change the data during every epoch DON'T use the data_loader
-            decorator.
-
         """
         return None
 
@@ -1257,9 +1254,6 @@ def val_dataloader(self):
         .. note:: If you don't need a validation dataset and a validation_step, you don't need to
             implement this method.
 
-        .. note:: If you want to change the data during every epoch DON'T use the data_loader
-            decorator.
-
         .. note:: In the case where you return multiple `val_dataloaders`, the `validation_step`
             will have an argument `dataset_idx` which matches the order here.
         """

pytorch_lightning/trainer/trainer.py

@@ -558,8 +558,9 @@ def fit(
             # feed to .fit()
 
         """
-        # bind logger
+        # bind logger and other properties
         model.logger = self.logger
+        self.copy_trainer_model_properties(model)
 
         # set up the passed in dataloaders (if needed)
         self.__attach_dataloaders(model, train_dataloader, val_dataloaders, test_dataloaders)