anomalib.models.ganomaly.torch_model

Torch models defining encoder, decoder, Generator and Discriminator.

Code adapted from https://github.com/samet-akcay/ganomaly.

Module Contents

Classes

Encoder

Encoder Network.

Decoder

Decoder Network.

Discriminator

Discriminator.

Generator

Generator model.

GanomalyModel

Ganomaly Model.
class anomalib.models.ganomaly.torch_model.Encoder(input_size: Tuple[int, int], latent_vec_size: int, num_input_channels: int, n_features: int, extra_layers: int = 0, add_final_conv_layer: bool = True)[source]

Bases: torch.nn.Module

Encoder Network.

Parameters

  • input_size (Tuple[int, int]) – Size of input image

  • latent_vec_size (int) – Size of latent vector z

  • num_input_channels (int) – Number of input channels in the image

  • n_features (int) – Number of features per convolution layer

  • extra_layers (int) – Number of extra layers since the network uses only a single encoder layer by default. Defaults to 0.

forward(self, input_tensor: torch.Tensor)[source]

Return latent vectors.

class anomalib.models.ganomaly.torch_model.Decoder(input_size: Tuple[int, int], latent_vec_size: int, num_input_channels: int, n_features: int, extra_layers: int = 0)[source]

Bases: torch.nn.Module

Decoder Network.

Parameters

  • input_size (Tuple[int, int]) – Size of input image

  • latent_vec_size (int) – Size of latent vector z

  • num_input_channels (int) – Number of input channels in the image

  • n_features (int) – Number of features per convolution layer

  • extra_layers (int) – Number of extra layers since the network uses only a single encoder layer by default. Defaults to 0.

forward(self, input_tensor)[source]

Return generated image.

class anomalib.models.ganomaly.torch_model.Discriminator(input_size: Tuple[int, int], num_input_channels: int, n_features: int, extra_layers: int = 0)[source]

Bases: torch.nn.Module

Discriminator.

Made of only one encoder layer which takes x and x_hat to produce a score.

Parameters

  • input_size (Tuple[int,int]) – Input image size.

  • num_input_channels (int) – Number of image channels.

  • n_features (int) – Number of feature maps in each convolution layer.

  • extra_layers (int, optional) – Add extra intermediate layers. Defaults to 0.

forward(self, input_tensor)[source]

Return class of object and features.

class anomalib.models.ganomaly.torch_model.Generator(input_size: Tuple[int, int], latent_vec_size: int, num_input_channels: int, n_features: int, extra_layers: int = 0, add_final_conv_layer: bool = True)[source]

Bases: torch.nn.Module

Generator model.

Made of an encoder-decoder-encoder architecture.

Parameters

  • input_size (Tuple[int,int]) – Size of input data.

  • latent_vec_size (int) – Dimension of latent vector produced between the first encoder-decoder.

  • num_input_channels (int) – Number of channels in input image.

  • n_features (int) – Number of feature maps in each convolution layer.

  • extra_layers (int, optional) – Extra intermediate layers in the encoder/decoder. Defaults to 0.

  • add_final_conv_layer (bool, optional) – Add a final convolution layer in the decoder. Defaults to True.

forward(self, input_tensor)[source]

Return generated image and the latent vectors.

class anomalib.models.ganomaly.torch_model.GanomalyModel(input_size: Tuple[int, int], num_input_channels: int, n_features: int, latent_vec_size: int, extra_layers: int = 0, add_final_conv_layer: bool = True)[source]

Bases: torch.nn.Module

Ganomaly Model.

Parameters

  • input_size (Tuple[int,int]) – Input dimension.

  • num_input_channels (int) – Number of input channels.

  • n_features (int) – Number of features layers in the CNNs.

  • latent_vec_size (int) – Size of autoencoder latent vector.

  • extra_layers (int, optional) – Number of extra layers for encoder/decoder. Defaults to 0.

  • add_final_conv_layer (bool, optional) – Add convolution layer at the end. Defaults to True.

static weights_init(module: torch.nn.Module)[source]

Initialize DCGAN weights.

Parameters

module (nn.Module) – [description]

forward(self, batch: torch.Tensor) → Union[Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor], torch.Tensor][source]

Get scores for batch.

Parameters

batch (Tensor) – Images

Returns

Regeneration scores.

Return type

Tensor