[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

course_UvA-DL/02-activation-functions/Activation_Functions.py

@@ -278,7 +278,7 @@ def vis_act_fn(act_fn, ax, x):
 # %%
 class BaseNetwork(nn.Module):
     def __init__(self, act_fn, input_size=784, num_classes=10, hidden_sizes=[512, 256, 256, 128]):
-        """Base Network
+        """Base Network.
 
         Args:
             act_fn: Object of the activation function that should be used as non-linearity in the network.
@@ -431,7 +431,7 @@ def save_model(model, model_path, model_name):
 
 # %%
 def visualize_gradients(net, color="C0"):
-    """Visualize gradients
+    """Visualize gradients.
 
     Args:
         net: Object of class BaseNetwork

course_UvA-DL/03-initialization-and-optimization/Initialization_and_Optimization.py

@@ -151,7 +151,7 @@
 # %%
 class BaseNetwork(nn.Module):
     def __init__(self, act_fn, input_size=784, num_classes=10, hidden_sizes=[512, 256, 256, 128]):
-        """Base Network
+        """Base Network.
 
         Args:
             act_fn: Object of the activation function that should be used as non-linearity in the network.

course_UvA-DL/04-inception-resnet-densenet/Inception_ResNet_DenseNet.py

@@ -417,7 +417,7 @@ def train_model(model_name, save_name=None, **kwargs):
 # %%
 class InceptionBlock(nn.Module):
     def __init__(self, c_in, c_red: dict, c_out: dict, act_fn):
-        """InceptionBlock
+        """InceptionBlock.
 
         Args:
             c_in - Number of input feature maps from the previous layers
@@ -667,7 +667,7 @@ def forward(self, x):
 
 class ResNetBlock(nn.Module):
     def __init__(self, c_in, act_fn, subsample=False, c_out=-1):
-        """ResNetBlock
+        """ResNetBlock.
 
         Inputs:
             c_in - Number of input features
@@ -713,7 +713,7 @@ def forward(self, x):
 # %%
 class PreActResNetBlock(nn.Module):
     def __init__(self, c_in, act_fn, subsample=False, c_out=-1):
-        """PreAct ResNet Block
+        """PreAct ResNet Block.
 
         Inputs:
             c_in - Number of input features
@@ -783,7 +783,7 @@ def __init__(
         block_name="ResNetBlock",
         **kwargs,
     ):
-        """ResNet
+        """ResNet.
 
         Inputs:
             num_classes - Number of classification outputs (10 for CIFAR10)
@@ -953,7 +953,7 @@ def forward(self, x):
 # %%
 class DenseLayer(nn.Module):
     def __init__(self, c_in, bn_size, growth_rate, act_fn):
-        """DenseLayer
+        """DenseLayer.
 
         Inputs:
             c_in - Number of input channels
@@ -985,7 +985,7 @@ def forward(self, x):
 # %%
 class DenseBlock(nn.Module):
     def __init__(self, c_in, num_layers, bn_size, growth_rate, act_fn):
-        """Dense Block
+        """Dense Block.
 
         Inputs:
             c_in - Number of input channels

course_UvA-DL/05-transformers-and-MH-attention/Transformers_MHAttention.py

@@ -463,7 +463,7 @@ def forward(self, x, mask=None, return_attention=False):
 # %%
 class EncoderBlock(nn.Module):
     def __init__(self, input_dim, num_heads, dim_feedforward, dropout=0.0):
-        """EncoderBlock
+        """EncoderBlock.
 
         Args:
             input_dim: Dimensionality of the input
@@ -573,7 +573,7 @@ def get_attention_maps(self, x, mask=None):
 # %%
 class PositionalEncoding(nn.Module):
     def __init__(self, d_model, max_len=5000):
-        """Positional Encoding
+        """Positional Encoding.
 
         Args:
             d_model: Hidden dimensionality of the input.
@@ -760,7 +760,7 @@ def __init__(
         dropout=0.0,
         input_dropout=0.0,
     ):
-        """TransformerPredictor
+        """TransformerPredictor.
 
         Args:
             input_dim: Hidden dimensionality of the input

course_UvA-DL/06-graph-neural-networks/GNN_overview.py

@@ -162,7 +162,7 @@ def __init__(self, c_in, c_out):
         self.projection = nn.Linear(c_in, c_out)
 
     def forward(self, node_feats, adj_matrix):
-        """forward
+        """Forward.
 
         Args:
             node_feats: Tensor with node features of shape [batch_size, num_nodes, c_in]
@@ -318,7 +318,7 @@ def __init__(self, c_in, c_out, num_heads=1, concat_heads=True, alpha=0.2):
         nn.init.xavier_uniform_(self.a.data, gain=1.414)
 
     def forward(self, node_feats, adj_matrix, print_attn_probs=False):
-        """forward
+        """Forward.
 
         Args:
             node_feats: Input features of the node. Shape: [batch_size, c_in]
@@ -499,7 +499,7 @@ def __init__(
         dp_rate=0.1,
         **kwargs,
     ):
-        """GNNModel
+        """GNNModel.
 
         Args:
             c_in: Dimension of input features
@@ -526,7 +526,7 @@ def __init__(
         self.layers = nn.ModuleList(layers)
 
     def forward(self, x, edge_index):
-        """forward
+        """Forward.
 
         Args:
             x: Input features per node
@@ -553,7 +553,7 @@ def forward(self, x, edge_index):
 # %%
 class MLPModel(nn.Module):
     def __init__(self, c_in, c_hidden, c_out, num_layers=2, dp_rate=0.1):
-        """MLPModel
+        """MLPModel.
 
         Args:
             c_in: Dimension of input features
@@ -572,7 +572,7 @@ def __init__(self, c_in, c_hidden, c_out, num_layers=2, dp_rate=0.1):
         self.layers = nn.Sequential(*layers)
 
     def forward(self, x, *args, **kwargs):
-        """forward
+        """Forward.
 
         Args:
             x: Input features per node
@@ -850,7 +850,7 @@ def print_results(result_dict):
 # %%
 class GraphGNNModel(nn.Module):
     def __init__(self, c_in, c_hidden, c_out, dp_rate_linear=0.5, **kwargs):
-        """GraphGNNModel
+        """GraphGNNModel.
 
         Args:
             c_in: Dimension of input features
@@ -864,7 +864,7 @@ def __init__(self, c_in, c_hidden, c_out, dp_rate_linear=0.5, **kwargs):
         self.head = nn.Sequential(nn.Dropout(dp_rate_linear), nn.Linear(c_hidden, c_out))
 
     def forward(self, x, edge_index, batch_idx):
-        """forward
+        """Forward.
 
         Args:
             x: Input features per node

course_UvA-DL/07-deep-energy-based-generative-models/Deep_Energy_Models.py

@@ -335,7 +335,7 @@ def forward(self, x):
 # %%
 class Sampler:
     def __init__(self, model, img_shape, sample_size, max_len=8192):
-        """Sampler
+        """Sampler.
 
         Args:
             model: Neural network to use for modeling E_theta

course_UvA-DL/08-deep-autoencoders/Deep_Autoencoders.py

@@ -131,7 +131,7 @@ def get_train_images(num):
 # %%
 class Encoder(nn.Module):
     def __init__(self, num_input_channels: int, base_channel_size: int, latent_dim: int, act_fn: object = nn.GELU):
-        """Encoder
+        """Encoder.
 
         Args:
            num_input_channels : Number of input channels of the image. For CIFAR, this parameter is 3
@@ -191,7 +191,7 @@ def forward(self, x):
 # %%
 class Decoder(nn.Module):
     def __init__(self, num_input_channels: int, base_channel_size: int, latent_dim: int, act_fn: object = nn.GELU):
-        """Decoder
+        """Decoder.
 
         Args:
            num_input_channels : Number of channels of the image to reconstruct. For CIFAR, this parameter is 3

course_UvA-DL/09-normalizing-flows/NF_image_modeling.py

@@ -261,7 +261,7 @@ def show_imgs(imgs, title=None, row_size=4):
 # %%
 class ImageFlow(L.LightningModule):
     def __init__(self, flows, import_samples=8):
-        """ImageFlow
+        """ImageFlow.
 
         Args:
             flows: A list of flows (each a nn.Module) that should be applied on the images.
@@ -402,7 +402,7 @@ def test_step(self, batch, batch_idx):
 # %%
 class Dequantization(nn.Module):
     def __init__(self, alpha=1e-5, quants=256):
-        """Dequantization
+        """Dequantization.
 
         Args:
             alpha: small constant that is used to scale the original input.
@@ -590,7 +590,7 @@ def visualize_dequantization(quants, prior=None):
 # %%
 class VariationalDequantization(Dequantization):
     def __init__(self, var_flows, alpha=1e-5):
-        """Variational Dequantization
+        """Variational Dequantization.
 
         Args:
             var_flows: A list of flow transformations to use for modeling q(u|x)
@@ -676,7 +676,7 @@ def __init__(self, network, mask, c_in):
         self.register_buffer("mask", mask)
 
     def forward(self, z, ldj, reverse=False, orig_img=None):
-        """forward
+        """Forward.
 
         Args:
             z: Latent input to the flow
@@ -804,8 +804,7 @@ def forward(self, x):
 
 class LayerNormChannels(nn.Module):
     def __init__(self, c_in, eps=1e-5):
-        """
-        This module applies layer norm across channels in an image.
+        """This module applies layer norm across channels in an image.
 
         Args:
             c_in: Number of channels of the input
@@ -826,8 +825,7 @@ def forward(self, x):
 
 class GatedConv(nn.Module):
     def __init__(self, c_in, c_hidden):
-        """
-        This module applies a two-layer convolutional ResNet block with input gate
+        """This module applies a two-layer convolutional ResNet block with input gate.
 
         Args:
             c_in: Number of channels of the input
@@ -1332,7 +1330,7 @@ def interpolate(model, img1, img2, num_steps=8):
 
 # %%
 def visualize_dequant_distribution(model: ImageFlow, imgs: Tensor, title: str = None):
-    """Visualize dequant distribution
+    """Visualize dequant distribution.
 
     Args:
         model: The flow of which we want to visualize the dequantization distribution

course_UvA-DL/11-vision-transformer/Vision_Transformer.py

@@ -209,7 +209,7 @@ def img_to_patch(x, patch_size, flatten_channels=True):
 # %%
 class AttentionBlock(nn.Module):
     def __init__(self, embed_dim, hidden_dim, num_heads, dropout=0.0):
-        """Attention Block
+        """Attention Block.
 
         Inputs:
             embed_dim - Dimensionality of input and attention feature vectors
@@ -269,7 +269,7 @@ def __init__(
         num_patches,
         dropout=0.0,
     ):
-        """Vision Transformer
+        """Vision Transformer.
 
         Inputs:
             embed_dim - Dimensionality of the input feature vectors to the Transformer

course_UvA-DL/12-meta-learning/Meta_Learning.py

@@ -257,7 +257,7 @@ def dataset_from_labels(imgs, targets, class_set, **kwargs):
 # %%
 class FewShotBatchSampler:
     def __init__(self, dataset_targets, N_way, K_shot, include_query=False, shuffle=True, shuffle_once=False):
-        """FewShot Batch Sampler
+        """FewShot Batch Sampler.
 
         Inputs:
             dataset_targets - PyTorch tensor of the labels of the data elements.
@@ -968,7 +968,7 @@ def validation_step(self, batch, batch_idx):
 # %%
 class TaskBatchSampler:
     def __init__(self, dataset_targets, batch_size, N_way, K_shot, include_query=False, shuffle=True):
-        """Task Batch Sampler
+        """Task Batch Sampler.
 
         Inputs:
             dataset_targets - PyTorch tensor of the labels of the data elements.

lightning_examples/reinforce-learning-DQN/dqn.py

@@ -21,7 +21,6 @@
 
 # %%
 class DQN(nn.Module):
-
     def __init__(self, obs_size: int, n_actions: int, hidden_size: int = 128):
         """Simple MLP network.
 
@@ -113,7 +112,6 @@ def __iter__(self) -> Iterator[Tuple]:
 
 # %%
 class Agent:
-
     def __init__(self, env: gym.Env, replay_buffer: ReplayBuffer) -> None:
         """Base Agent class handeling the interaction with the environment.
 
@@ -193,7 +191,6 @@ def play_step(
 
 # %%
 class DQNLightning(LightningModule):
-
     def __init__(
         self,
         batch_size: int = 16,