MNISTMLP#

Classes#

class backbone.MNISTMLP.BaseMNISTMLP(input_size, output_size, hidden_size=100)[source]#

Bases: MammothBackbone

Network composed of two hidden layers, each containing 100 ReLU activations. Designed for the MNIST dataset.

forward(x, returnt='out')[source]#

Compute a forward pass.

Parameters:

x (Tensor) – input tensor (batch_size, input_size)

Returns:

output tensor (output_size)

Return type:

Tensor

reset_parameters()[source]#

Calls the Xavier parameter initialization function.

Functions#

backbone.MNISTMLP.mnistmlp(mlp_hidden_size=100)[source]#
Return type:

BaseMNISTMLP