diff --git a/pl_examples/README.md b/pl_examples/README.md
index 443a15f7..5757d64f 100644
--- a/pl_examples/README.md
+++ b/pl_examples/README.md
@@ -1,11 +1,14 @@
 # Examples   
-This folder has 3 sections:   
-
-### Domain templates   
-These are templates to show common approaches such as GANs and RL.   
+This folder has 4 sections:   
 
 ### Basic examples   
 These show the most common use of Lightning for either CPU or GPU training.   
 
+### Domain templates   
+These are templates to show common approaches such as GANs and RL.   
+
+### Full examples 
+Contains examples demonstrating ImageNet training, Semantic Segmentation, etc.
+
 ### Multi-node examples   
 These show how to run jobs on a GPU cluster using lightning.
\ No newline at end of file
diff --git a/pl_examples/basic_examples/README.md b/pl_examples/basic_examples/README.md
index 4e8e9b47..9faae5a3 100644
--- a/pl_examples/basic_examples/README.md
+++ b/pl_examples/basic_examples/README.md
@@ -31,7 +31,7 @@ python gpu_template.py --gpus 2 --distributed_backend ddp
 ---
 #### DistributedDataParallel+DP (ddp2)    
 
-Train on multiple GPUs using DistributedDataParallel + dataparallel.
+Train on multiple GPUs using DistributedDataParallel + DataParallel.
 On a single node, uses all GPUs for 1 model. Then shares gradient information
 across nodes.   
 ```bash
diff --git a/pl_examples/basic_examples/cpu_template.py b/pl_examples/basic_examples/cpu_template.py
index 7781ba32..537c4cdc 100644
--- a/pl_examples/basic_examples/cpu_template.py
+++ b/pl_examples/basic_examples/cpu_template.py
@@ -1,5 +1,5 @@
 """
-Runs a model on a single node across N-gpus.
+Runs a model on the CPU on a single node.
 """
 import os
 from argparse import ArgumentParser
diff --git a/pl_examples/basic_examples/gpu_template.py b/pl_examples/basic_examples/gpu_template.py
index 090b2adc..b51c3770 100644
--- a/pl_examples/basic_examples/gpu_template.py
+++ b/pl_examples/basic_examples/gpu_template.py
@@ -1,5 +1,5 @@
 """
-Runs a model on a single node across N-gpus.
+Runs a model on a single node across multiple gpus.
 """
 import os
 from argparse import ArgumentParser
diff --git a/pl_examples/basic_examples/lightning_module_template.py b/pl_examples/basic_examples/lightning_module_template.py
index b6444cee..c5a7f939 100644
--- a/pl_examples/basic_examples/lightning_module_template.py
+++ b/pl_examples/basic_examples/lightning_module_template.py
@@ -1,5 +1,5 @@
 """
-Example template for defining a system
+Example template for defining a system.
 """
 import os
 from argparse import ArgumentParser
@@ -41,8 +41,7 @@ class LightningTemplateModel(LightningModule):
 
     def __init__(self, hparams):
         """
-        Pass in parsed HyperOptArgumentParser to the model
-        :param hparams:
+        Pass in hyperparameters as a `argparse.Namespace` or a `dict` to the model.
         """
         # init superclass
         super().__init__()
@@ -61,8 +60,7 @@ class LightningTemplateModel(LightningModule):
     # ---------------------
     def __build_model(self):
         """
-        Layout model
-        :return:
+        Layout the model.
         """
         self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
                               out_features=self.hparams.hidden_dim)
@@ -77,11 +75,9 @@ class LightningTemplateModel(LightningModule):
     # ---------------------
     def forward(self, x):
         """
-        No special modification required for lightning, define as you normally would
-        :param x:
-        :return:
+        No special modification required for Lightning, define it as you normally would
+        in the `nn.Module` in vanilla PyTorch.
         """
-
         x = self.c_d1(x)
         x = torch.tanh(x)
         x = self.c_d1_bn(x)
@@ -98,9 +94,8 @@ class LightningTemplateModel(LightningModule):
 
     def training_step(self, batch, batch_idx):
         """
-        Lightning calls this inside the training loop
-        :param batch:
-        :return:
+        Lightning calls this inside the training loop with the data from the training dataloader
+        passed in as `batch`.
         """
         # forward pass
         x, y = batch
@@ -123,9 +118,8 @@ class LightningTemplateModel(LightningModule):
 
     def validation_step(self, batch, batch_idx):
         """
-        Lightning calls this inside the validation loop
-        :param batch:
-        :return:
+        Lightning calls this inside the validation loop with the data from the validation dataloader
+        passed in as `batch`.
         """
         x, y = batch
         x = x.view(x.size(0), -1)
@@ -151,9 +145,8 @@ class LightningTemplateModel(LightningModule):
 
     def validation_epoch_end(self, outputs):
         """
-        Called at the end of validation to aggregate outputs
-        :param outputs: list of individual outputs of each validation step
-        :return:
+        Called at the end of validation to aggregate outputs.
+        :param outputs: list of individual outputs of each validation step.
         """
         # 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)
@@ -187,8 +180,8 @@ class LightningTemplateModel(LightningModule):
     # ---------------------
     def configure_optimizers(self):
         """
-        return whatever optimizers we want here
-        :return: list of optimizers
+        Return whatever optimizers and learning rate schedulers you want here.
+        At least one optimizer is required.
         """
         optimizer = optim.Adam(self.parameters(), lr=self.hparams.learning_rate)
         scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
@@ -234,9 +227,8 @@ class LightningTemplateModel(LightningModule):
 
     def test_step(self, batch, batch_idx):
         """
-        Lightning calls this during testing, similar to val_step
-        :param batch:
-        :return:val
+        Lightning calls this during testing, similar to `validation_step`,
+        with the data from the test dataloader passed in as `batch`.
         """
         output = self.validation_step(batch, batch_idx)
         # Rename output keys
@@ -247,9 +239,8 @@ class LightningTemplateModel(LightningModule):
 
     def test_epoch_end(self, outputs):
         """
-        Called at the end of test to aggregate outputs, similar to validation_epoch_end
-        :param outputs: list of individual outputs of each validation step
-        :return:
+        Called at the end of test to aggregate outputs, similar to `validation_epoch_end`.
+        :param outputs: list of individual outputs of each test step
         """
         results = self.validation_step_end(outputs)
 
@@ -266,10 +257,7 @@ class LightningTemplateModel(LightningModule):
     @staticmethod
     def add_model_specific_args(parent_parser, root_dir):  # pragma: no-cover
         """
-        Parameters you define here will be available to your model through self.hparams
-        :param parent_parser:
-        :param root_dir:
-        :return:
+        Parameters you define here will be available to your model through `self.hparams`.
         """
         parser = ArgumentParser(parents=[parent_parser])
 
diff --git a/pl_examples/domain_templates/gan.py b/pl_examples/domain_templates/gan.py
index 3661b363..795876e2 100644
--- a/pl_examples/domain_templates/gan.py
+++ b/pl_examples/domain_templates/gan.py
@@ -2,7 +2,7 @@
 To run this template just do:
 python gan.py
 
-After a few epochs, launch tensorboard to see the images being generated at every batch.
+After a few epochs, launch TensorBoard to see the images being generated at every batch:
 
 tensorboard --logdir default
 """
diff --git a/pl_examples/domain_templates/reinforse_learn_Qnet.py b/pl_examples/domain_templates/reinforce_learn_Qnet.py
similarity index 95%
rename from pl_examples/domain_templates/reinforse_learn_Qnet.py
rename to pl_examples/domain_templates/reinforce_learn_Qnet.py
index 5a797d7d..4301957a 100644
--- a/pl_examples/domain_templates/reinforse_learn_Qnet.py
+++ b/pl_examples/domain_templates/reinforce_learn_Qnet.py
@@ -1,17 +1,17 @@
 """
-# Deep Reinforcement Learning: Deep Q-network (DQN)
+Deep Reinforcement Learning: Deep Q-network (DQN)
 
-this example is based off https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-
+This example is based on https://github.com/PacktPublishing/Deep-Reinforcement-Learning-Hands-On-
 Second-Edition/blob/master/Chapter06/02_dqn_pong.py
 
 The template illustrates using Lightning for Reinforcement Learning. The example builds a basic DQN using the
 classic CartPole environment.
 
-to run the template just run:
-python dqn.py
+To run the template just run:
+python reinforce_learn_Qnet.py
 
-After ~1500 steps, you will see the total_reward hitting the max score of 200. Open up tensor boards to
-see the metrics.
+After ~1500 steps, you will see the total_reward hitting the max score of 200. Open up TensorBoard to
+see the metrics:
 
 tensorboard --logdir default
 """
@@ -72,7 +72,7 @@ class ReplayBuffer:
     def __init__(self, capacity: int) -> None:
         self.buffer = deque(maxlen=capacity)
 
-    def __len__(self) -> None:
+    def __len__(self) -> int:
         return len(self.buffer)
 
     def append(self, experience: Experience) -> None:
@@ -128,7 +128,7 @@ class Agent:
         self.state = self.env.reset()
 
     def reset(self) -> None:
-        """ Resents the environment and updates the state"""
+        """Resets the environment and updates the state"""
         self.state = self.env.reset()
 
     def get_action(self, net: nn.Module, epsilon: float, device: str) -> int:
@@ -220,7 +220,7 @@ class DQNLightning(pl.LightningModule):
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         """
-        Passes in a state x through the network and gets the q_values of each action as an output
+        Passes in a state `x` through the network and gets the `q_values` of each action as an output
 
         Args:
             x: environment state
@@ -292,7 +292,7 @@ class DQNLightning(pl.LightningModule):
         return OrderedDict({'loss': loss, 'log': log, 'progress_bar': log})
 
     def configure_optimizers(self) -> List[Optimizer]:
-        """ Initialize Adam optimizer"""
+        """Initialize Adam optimizer"""
         optimizer = optim.Adam(self.net.parameters(), lr=self.hparams.lr)
         return [optimizer]
 
diff --git a/pl_examples/full_examples/semantic_segmentation/models/unet/model.py b/pl_examples/full_examples/semantic_segmentation/models/unet/model.py
index 484c6982..e858ed2f 100644
--- a/pl_examples/full_examples/semantic_segmentation/models/unet/model.py
+++ b/pl_examples/full_examples/semantic_segmentation/models/unet/model.py
@@ -4,15 +4,15 @@ from models.unet.parts import DoubleConv, Down, Up
 
 
 class UNet(nn.Module):
-    '''
+    """
     Architecture based on U-Net: Convolutional Networks for Biomedical Image Segmentation
     Link - https://arxiv.org/abs/1505.04597
 
     Parameters:
-        num_classes (int) - Number of output classes required (default 19 for KITTI dataset)
-        bilinear (bool) - Whether to use bilinear interpolation or transposed
-        convolutions for upsampling.
-    '''
+        num_classes (int): Number of output classes required (default 19 for KITTI dataset)
+        bilinear (bool): Whether to use bilinear interpolation or transposed
+            convolutions for upsampling.
+    """
 
     def __init__(self, num_classes=19, bilinear=False):
         super().__init__()
diff --git a/pl_examples/full_examples/semantic_segmentation/models/unet/parts.py b/pl_examples/full_examples/semantic_segmentation/models/unet/parts.py
index 6828c3f7..8036ea05 100644
--- a/pl_examples/full_examples/semantic_segmentation/models/unet/parts.py
+++ b/pl_examples/full_examples/semantic_segmentation/models/unet/parts.py
@@ -4,10 +4,10 @@ import torch.nn.functional as F
 
 
 class DoubleConv(nn.Module):
-    '''
+    """
     Double Convolution and BN and ReLU
     (3x3 conv -> BN -> ReLU) ** 2
-    '''
+    """
 
     def __init__(self, in_ch, out_ch):
         super().__init__()
@@ -25,9 +25,9 @@ class DoubleConv(nn.Module):
 
 
 class Down(nn.Module):
-    '''
+    """
     Combination of MaxPool2d and DoubleConv in series
-    '''
+    """
 
     def __init__(self, in_ch, out_ch):
         super().__init__()
@@ -41,11 +41,11 @@ class Down(nn.Module):
 
 
 class Up(nn.Module):
-    '''
+    """
     Upsampling (by either bilinear interpolation or transpose convolutions)
     followed by concatenation of feature map from contracting path,
     followed by double 3x3 convolution.
-    '''
+    """
 
     def __init__(self, in_ch, out_ch, bilinear=False):
         super().__init__()
diff --git a/pl_examples/full_examples/semantic_segmentation/semseg.py b/pl_examples/full_examples/semantic_segmentation/semseg.py
index dfac9e9c..5426dfa2 100644
--- a/pl_examples/full_examples/semantic_segmentation/semseg.py
+++ b/pl_examples/full_examples/semantic_segmentation/semseg.py
@@ -13,8 +13,8 @@ import pytorch_lightning as pl
 
 
 class KITTI(Dataset):
-    '''
-    Dataset Class for KITTI Semantic Segmentation Benchmark dataset
+    """
+    Class for KITTI Semantic Segmentation Benchmark dataset
     Dataset link - http://www.cvlibs.net/datasets/kitti/eval_semseg.php?benchmark=semantics2015
 
     There are 34 classes in the given labels. However, not all of them are useful for training
@@ -33,7 +33,7 @@ class KITTI(Dataset):
     In the `get_item` function, images and masks are resized to the given `img_size`, masks are
     encoded using `encode_segmap`, and given `transform` (if any) are applied to the image only
     (mask does not usually require transforms, but they can be implemented in a similar way).
-    '''
+    """
 
     def __init__(
         self,
@@ -67,7 +67,7 @@ class KITTI(Dataset):
             self.mask_list = None
 
     def __len__(self):
-        return(len(self.img_list))
+        return len(self.img_list)
 
     def __getitem__(self, idx):
         img = Image.open(self.img_list[idx])
@@ -89,9 +89,9 @@ class KITTI(Dataset):
             return img
 
     def encode_segmap(self, mask):
-        '''
+        """
         Sets void classes to zero so they won't be considered for training
-        '''
+        """
         for voidc in self.void_labels:
             mask[mask == voidc] = self.ignore_index
         for validc in self.valid_labels:
@@ -99,9 +99,9 @@ class KITTI(Dataset):
         return mask
 
     def get_filenames(self, path):
-        '''
+        """
         Returns a list of absolute paths to images inside given `path`
-        '''
+        """
         files_list = list()
         for filename in os.listdir(path):
             files_list.append(os.path.join(path, filename))
@@ -109,7 +109,7 @@ class KITTI(Dataset):
 
 
 class SegModel(pl.LightningModule):
-    '''
+    """
     Semantic Segmentation Module
 
     This is a basic semantic segmentation module implemented with Lightning.
@@ -120,7 +120,7 @@ class SegModel(pl.LightningModule):
     It uses the FCN ResNet50 model as an example.
 
     Adam optimizer is used along with Cosine Annealing learning rate scheduler.
-    '''
+    """
 
     def __init__(self, hparams):
         super().__init__()
diff --git a/pl_examples/multi_node_examples/README.md b/pl_examples/multi_node_examples/README.md
index 63315ff9..f4bb719d 100644
--- a/pl_examples/multi_node_examples/README.md
+++ b/pl_examples/multi_node_examples/README.md
@@ -8,13 +8,13 @@ To run this demo do the following:
 3. Choose a script to submit    
 
 #### DDP  
-Submit this job to run with distributedDataParallel (2 nodes, 2 gpus each)
+Submit this job to run with DistributedDataParallel (2 nodes, 2 gpus each)
 ```bash
 sbatch ddp_job_submit.sh YourEnv
 ```
 
 #### DDP2  
-Submit this job to run with a different implementation of distributedDataParallel.
+Submit this job to run with a different implementation of DistributedDataParallel.
 In this version, each node acts like DataParallel but syncs across nodes like DDP.
 ```bash
 sbatch ddp2_job_submit.sh YourEnv
diff --git a/pl_examples/multi_node_examples/multi_node_ddp2_demo.py b/pl_examples/multi_node_examples/multi_node_ddp2_demo.py
index d88ee08a..6abf8739 100644
--- a/pl_examples/multi_node_examples/multi_node_ddp2_demo.py
+++ b/pl_examples/multi_node_examples/multi_node_ddp2_demo.py
@@ -16,11 +16,7 @@ np.random.seed(SEED)
 
 
 def main(hparams):
-    """
-    Main training routine specific for this project
-    :param hparams:
-    :return:
-    """
+    """Main training routine specific for this project."""
     # ------------------------
     # 1 INIT LIGHTNING MODEL
     # ------------------------