diff --git a/examples/__init__.py b/examples/__init__.py
index 6743d7f9..0d456dac 100644
--- a/examples/__init__.py
+++ b/examples/__init__.py
@@ -1 +1,5 @@
-from .new_project_templates.lightning_module_template import LightningTemplateModel
\ No newline at end of file
+from .new_project_templates.lightning_module_template import LightningTemplateModel
+
+__all__ = [
+    'LightningTemplateModel'
+]
diff --git a/examples/new_project_templates/lightning_module_template.py b/examples/new_project_templates/lightning_module_template.py
index 483a4e3a..a6550035 100644
--- a/examples/new_project_templates/lightning_module_template.py
+++ b/examples/new_project_templates/lightning_module_template.py
@@ -182,7 +182,7 @@ class LightningTemplateModel(LightningModule):
             if self.on_gpu:
                 train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
                 batch_size = batch_size // self.trainer.world_size  # scale batch size
-        except Exception as e:
+        except Exception:
             pass
 
         should_shuffle = train_sampler is None
@@ -211,7 +211,7 @@ class LightningTemplateModel(LightningModule):
         return self.__dataloader(train=False)
 
     @staticmethod
-    def add_model_specific_args(parent_parser, root_dir): # pragma: no cover
+    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:
@@ -224,20 +224,21 @@ class LightningTemplateModel(LightningModule):
         # parser.set_defaults(gradient_clip=5.0)
 
         # network params
-        parser.add_argument('--in_features', default=28*28, type=int)
+        parser.add_argument('--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
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
         parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
 
         # 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],
+        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,
+        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
diff --git a/examples/new_project_templates/trainer_cpu_template.py b/examples/new_project_templates/trainer_cpu_template.py
index de6ba7c4..21d705c6 100644
--- a/examples/new_project_templates/trainer_cpu_template.py
+++ b/examples/new_project_templates/trainer_cpu_template.py
@@ -67,7 +67,7 @@ if __name__ == '__main__':
     add_default_args(parent_parser, root_dir)
 
     # allow model to overwrite or extend args
-    parser = ExampleModel.add_model_specific_args(parent_parser)
+    parser = LightningTemplateModel.add_model_specific_args(parent_parser)
     hyperparams = parser.parse_args()
 
     # train model
diff --git a/pytorch_lightning/__init__.py b/pytorch_lightning/__init__.py
index 235590f2..145d3bd0 100644
--- a/pytorch_lightning/__init__.py
+++ b/pytorch_lightning/__init__.py
@@ -11,3 +11,9 @@ __copyright__ = 'Copyright (c) 2018-2019, %s.' % __author__
 __doc__ = """
 The Keras for ML researchers using PyTorch
 """
+
+__all__ = [
+    'Trainer',
+    'LightningModule',
+    'data_loader',
+]
diff --git a/pytorch_lightning/callbacks/__init__.py b/pytorch_lightning/callbacks/__init__.py
index f180c254..035deb06 100644
--- a/pytorch_lightning/callbacks/__init__.py
+++ b/pytorch_lightning/callbacks/__init__.py
@@ -1 +1,6 @@
-from .pt_callbacks import EarlyStopping, ModelCheckpoint
\ No newline at end of file
+from .pt_callbacks import EarlyStopping, ModelCheckpoint
+
+__all__ = [
+    'EarlyStopping',
+    'ModelCheckpoint',
+]
diff --git a/pytorch_lightning/callbacks/pt_callbacks.py b/pytorch_lightning/callbacks/pt_callbacks.py
index 89c8f6b2..f07c6a28 100644
--- a/pytorch_lightning/callbacks/pt_callbacks.py
+++ b/pytorch_lightning/callbacks/pt_callbacks.py
@@ -122,9 +122,9 @@ class EarlyStopping(Callback):
         current = logs.get(self.monitor)
         stop_training = False
         if current is None:
-            print('Early stopping conditioned on metric `%s` ''which is not available. Available metrics are: %s' %
-                (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning
-            )
+            print('Early stopping conditioned on metric `%s` '
+                  'which is not available. Available metrics are: %s' %
+                  (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning)
             exit(-1)
 
         if self.monitor_op(current - self.min_delta, self.best):
@@ -188,8 +188,7 @@ class ModelCheckpoint(Callback):
 
         if mode not in ['auto', 'min', 'max']:
             print('ModelCheckpoint mode %s is unknown, '
-                          'fallback to auto mode.' % (mode),
-                          RuntimeWarning)
+                  'fallback to auto mode.' % (mode), RuntimeWarning)
             mode = 'auto'
 
         if mode == 'min':
@@ -233,8 +232,8 @@ class ModelCheckpoint(Callback):
             if self.save_best_only:
                 current = logs.get(self.monitor)
                 if current is None:
-                    print('Can save best model only with %s available, '
-                                  'skipping.' % (self.monitor), RuntimeWarning)
+                    print('Can save best model only with %s available,'
+                          ' skipping.' % (self.monitor), RuntimeWarning)
                 else:
                     if self.monitor_op(current, self.best):
                         if self.verbose > 0:
diff --git a/pytorch_lightning/models/trainer.py b/pytorch_lightning/models/trainer.py
index 2a73d867..c0f67d7a 100644
--- a/pytorch_lightning/models/trainer.py
+++ b/pytorch_lightning/models/trainer.py
@@ -1,12 +1,10 @@
 """
 The trainer handles all the logic for running a val loop, training loop, distributing, etc...
 """
-import subprocess
-import traceback
-import warnings
+
 import os
-import pdb
 import re
+import warnings
 
 import numpy as np
 import tqdm
@@ -201,7 +199,7 @@ class Trainer(TrainerIO):
             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:
+            except Exception:
                 # likely not on slurm, so set the slurm managed flag to false
                 self.is_slurm_managing_tasks = False
 
@@ -235,13 +233,13 @@ class Trainer(TrainerIO):
             print('using 16bit precision')
 
         if use_amp and not APEX_AVAILABLE:  # pragma: no cover
-            msg = '''
+            msg = """
             You set use_amp=True but do not have apex installed.
-            Install apex first using this guide and rerun with use_amp=True: 
+            Install apex first using this guide and rerun with use_amp=True:
             https://github.com/NVIDIA/apex#linux
-            
+
             this run will NOT use 16 bit precision
-            '''
+            """
             raise ModuleNotFoundError(msg)
 
     @property
@@ -275,7 +273,7 @@ class Trainer(TrainerIO):
             'tng_loss': '{0:.3f}'.format(self.avg_loss),
             'v_nb': '{}'.format(self.experiment.version),
             'epoch': '{}'.format(self.current_epoch),
-            'batch_nb':'{}'.format(self.batch_nb),
+            'batch_nb': '{}'.format(self.batch_nb),
         }
         tqdm_dic.update(self.tqdm_metrics)
 
@@ -389,18 +387,18 @@ class Trainer(TrainerIO):
         self.val_dataloader = model.val_dataloader
 
         if self.use_ddp and not isinstance(self.tng_dataloader.sampler, DistributedSampler):
-            msg = '''
+            msg = """
             when using multiple gpus and multiple nodes you must pass a DistributedSampler to DataLoader(sampler).
-            
+
             ie: this:
             dataset = myDataset()
             dataloader = Dataloader(dataset)
-            
+
             becomes:
             dataset = myDataset()
             dist_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
             dataloader = Dataloader(dataset, sampler=dist_sampler)
-            '''
+            """
             raise MisconfigurationException(msg)
 
     # -----------------------------
@@ -418,8 +416,8 @@ class Trainer(TrainerIO):
                 self.ddp_train(task, model)
             else:
                 msg = f"""
-                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. 
+                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!
                 """
@@ -484,7 +482,7 @@ class Trainer(TrainerIO):
         try:
             node_id = os.environ['SLURM_NODEID']
             self.node_rank = int(node_id)
-        except Exception as e:
+        except Exception:
             self.node_rank = 0
 
         # recover original exp before went into process
@@ -543,14 +541,14 @@ class Trainer(TrainerIO):
         # sets the appropriate port
         try:
             port = os.environ['MASTER_PORT']
-        except Exception as e:
+        except Exception:
             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:
+        except Exception:
             root_node = '127.0.0.2'
 
         root_node = self.resolve_root_node_address(root_node)
@@ -773,14 +771,14 @@ class Trainer(TrainerIO):
 
         try:
             model_specific_tqdm_metrics_dic = output['prog']
-        except Exception as e:
+        except Exception:
             model_specific_tqdm_metrics_dic = {}
 
         # if output dict doesn't have the keyword loss
         # then assume the output=loss if scalar
         try:
             loss = output['loss']
-        except Exception as e:
+        except Exception:
             if type(output) is torch.Tensor:
                 loss = output
 
diff --git a/pytorch_lightning/pt_overrides/override_data_parallel.py b/pytorch_lightning/pt_overrides/override_data_parallel.py
index f06f8030..ab88d286 100644
--- a/pytorch_lightning/pt_overrides/override_data_parallel.py
+++ b/pytorch_lightning/pt_overrides/override_data_parallel.py
@@ -63,7 +63,6 @@ class LightningDataParallel(DataParallel):
         outputs = self.parallel_apply(replicas, inputs, kwargs)
         return self.gather(outputs, self.output_device)
 
-
     def parallel_apply(self, replicas, inputs, kwargs):
         return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
 
diff --git a/pytorch_lightning/root_module/grads.py b/pytorch_lightning/root_module/grads.py
index d50fa450..b28cf21c 100644
--- a/pytorch_lightning/root_module/grads.py
+++ b/pytorch_lightning/root_module/grads.py
@@ -4,6 +4,7 @@ Module to describe gradients
 
 from torch import nn
 
+
 class GradInformation(nn.Module):
 
     def grad_norm(self, norm_type):
@@ -17,11 +18,10 @@ class GradInformation(nn.Module):
                     norm = param_norm ** (1 / norm_type)
 
                     results['grad_{}_norm_{}'.format(norm_type, i)] = round(norm.data.cpu().numpy().flatten()[0], 3)
-                except Exception as e:
+                except Exception:
                     # this param had no grad
                     pass
 
         total_norm = total_norm ** (1. / norm_type)
         results['grad_{}_norm_total'.format(norm_type)] = round(total_norm.data.cpu().numpy().flatten()[0], 3)
         return results
-
diff --git a/pytorch_lightning/root_module/hooks.py b/pytorch_lightning/root_module/hooks.py
index 849826a8..00ece234 100644
--- a/pytorch_lightning/root_module/hooks.py
+++ b/pytorch_lightning/root_module/hooks.py
@@ -43,4 +43,3 @@ class ModelHooks(torch.nn.Module):
         :return:
         """
         pass
-
diff --git a/pytorch_lightning/root_module/memory.py b/pytorch_lightning/root_module/memory.py
index 128fb16f..a0ec9aa0 100644
--- a/pytorch_lightning/root_module/memory.py
+++ b/pytorch_lightning/root_module/memory.py
@@ -94,7 +94,7 @@ class ModelSummary(object):
         mods = list(self.model.modules())
         sizes = []
 
-        for i in range(1,len(mods)):
+        for i in range(1, len(mods)):
             m = mods[i]
             p = list(m.parameters())
             modsz = []
@@ -127,7 +127,7 @@ class ModelSummary(object):
         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 = pd.DataFrame(np.zeros((len(self.layer_names), len(cols))))
         df.columns = cols
 
         df['Name'] = self.layer_names
@@ -152,16 +152,16 @@ class ModelSummary(object):
         self.make_summary()
 
 
-def print_mem_stack(): # pragma: no cover
+def print_mem_stack():  # pragma: no cover
     for obj in gc.get_objects():
         try:
             if torch.is_tensor(obj) or (hasattr(obj, 'data') and torch.is_tensor(obj.data)):
                 print(type(obj), obj.size())
-        except Exception as e:
+        except Exception:
             pass
 
 
-def count_mem_items(): # pragma: no cover
+def count_mem_items():  # pragma: no cover
     nb_params = 0
     nb_tensors = 0
     for obj in gc.get_objects():
@@ -172,7 +172,7 @@ def count_mem_items(): # pragma: no cover
                     nb_params += 1
                 else:
                     nb_tensors += 1
-        except Exception as e:
+        except Exception:
             pass
 
     return nb_params, nb_tensors
diff --git a/pytorch_lightning/root_module/root_module.py b/pytorch_lightning/root_module/root_module.py
index 1421a72d..96dbfdcd 100644
--- a/pytorch_lightning/root_module/root_module.py
+++ b/pytorch_lightning/root_module/root_module.py
@@ -129,6 +129,3 @@ class LightningModule(GradInformation, ModelIO, ModelHooks):
     def unfreeze(self):
         for param in self.parameters():
             param.requires_grad = True
-
-
-
diff --git a/pytorch_lightning/testing/lm_test_module.py b/pytorch_lightning/testing/lm_test_module.py
index 9861810e..24995c7f 100644
--- a/pytorch_lightning/testing/lm_test_module.py
+++ b/pytorch_lightning/testing/lm_test_module.py
@@ -202,7 +202,7 @@ class LightningTestModel(LightningModule):
             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:
+        except Exception:
             pass
 
         should_shuffle = train_sampler is None
@@ -242,19 +242,20 @@ class LightningTestModel(LightningModule):
 
         # 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('--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
+        # use 500 for CPU, 50000 for GPU to see speed difference
+        parser.add_argument('--hidden_dim', default=50000, type=int)
 
         # data
         parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
 
         # training params (opt)
-        parser.opt_list('--learning_rate', default=0.001*8, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
+        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,
+        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
diff --git a/pytorch_lightning/utilities/arg_parse.py b/pytorch_lightning/utilities/arg_parse.py
index f274e751..44399c39 100644
--- a/pytorch_lightning/utilities/arg_parse.py
+++ b/pytorch_lightning/utilities/arg_parse.py
@@ -3,6 +3,9 @@ List of default args which mught be useful for all the available flags
 Might need to update with the new flags
 """
 
+import os
+
+
 def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None):
 
     # tng, test, val check intervals
@@ -44,7 +47,7 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
     # test_tube settings
     parser.add_argument('-en', '--tt_name', default='pt_test')
     parser.add_argument('-td', '--tt_description', default='pytorch lightning test')
-    parser.add_argument('--tt_save_path', default=root_dir + '/test_tube_logs', help='logging dir')
+    parser.add_argument('--tt_save_path', default=os.path.join(root_dir, 'test_tube_logs'), help='logging dir')
     parser.add_argument('--enable_single_run', dest='single_run', action='store_true')
     parser.add_argument('--nb_hopt_trials', default=1, type=int)
     parser.add_argument('--log_stdout', dest='log_stdout', action='store_true')
@@ -55,8 +58,7 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
     parser.add_argument('--default_tensor_type', default='torch.cuda.FloatTensor', type=str)
     parser.add_argument('--use_amp', dest='use_amp', action='store_true')
     parser.add_argument('--check_grad_nans', dest='check_grad_nans', action='store_true')
-    parser.add_argument('--amp_level', default='O2',type=str)
-
+    parser.add_argument('--amp_level', default='O2', type=str)
 
     # run on hpc
     parser.add_argument('--on_cluster', dest='on_cluster', action='store_true')
diff --git a/tests/debug.py b/tests/debug.py
index 09e9186b..fb0109a0 100644
--- a/tests/debug.py
+++ b/tests/debug.py
@@ -61,8 +61,8 @@ def get_model():
     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,
+                           'in_features': 28 * 28,
+                           'learning_rate': 0.001 * 8,
                            'optimizer_name': 'adam',
                            'data_root': os.path.join(root_dir, 'mnist'),
                            'out_features': 10,
diff --git a/tests/test_models.py b/tests/test_models.py
index 73ba2e43..fbf36442 100644
--- a/tests/test_models.py
+++ b/tests/test_models.py
@@ -136,11 +136,9 @@ def test_cpu_slurm_save_load():
 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.tag({'some_str': 'a_str', 'an_int': 1, 'a_float': 2.0})
     exp.argparse(hparams)
     exp.save()
 
@@ -502,7 +500,6 @@ def test_multi_gpu_model_ddp():
     run_gpu_model_test(trainer_options, model, hparams)
 
 
-
 def test_ddp_sampler_error():
     """
     Make sure DDP + AMP work
@@ -587,8 +584,8 @@ def get_hparams(continue_training=False, hpc_exp_number=0):
     args = {
         'drop_prob': 0.2,
         'batch_size': 32,
-        'in_features': 28*28,
-        'learning_rate': 0.001*8,
+        'in_features': 28 * 28,
+        'learning_rate': 0.001 * 8,
         'optimizer_name': 'adam',
         'data_root': os.path.join(root_dir, 'mnist'),
         'out_features': 10,