model_tf module

class model_tf.Discriminator(*args, **kwargs)[source]

Bases: Model

Discriminator class responsible for initializing and processing the discriminator network.

Parameters:

input_dim (int) – Dimension of the input features.
spec_norm (bool) – Whether to apply spectral normalization to the layers.
bounded (bool) – Whether to apply bounded activation on the final output.
layers_list (list) – List of integers specifying the number of units for each hidden layer.

bounded_activation(x)[source]: Activation function to apply bounded output using tanh.

bounded_activation()[source]

Apply a bounded activation using the tanh function, constraining the output within [-M, M].

call(inputs)[source]

Forward pass through the discriminator.

class model_tf.DiscriminatorMNIST(*args, **kwargs)[source]

Bases: Model

Discriminator class for the MNIST dataset, responsible for classifying real vs fake images.

Returns:: Output after processing the input image through the discriminator network.
Return type:: tf.Tensor

Forward pass through the MNIST discriminator.

Parameters:: x (tf.Tensor) – Input image data reshaped to (batch_size, 784).
Returns:: Output after processing through dense and normalization layers.
Return type:: tf.Tensor

class model_tf.Generator(*args, **kwargs)[source]

Bases: Model

Generator class responsible for initializing and processing the generator network.

Parameters:

X_dim (int) – Dimension of the output generated by the generator.
Z_dim (int) – Dimension of the input latent space.
spec_norm (bool) – Whether to apply spectral normalization to the layers.
layers_list (list) – List of integers specifying the number of units for each hidden layer.

call(inputs)[source]

Forward pass through the generator.