whestbench.
API

run_mlp_all_layers

Forward pass returning activations after each layer.

function · source

run_mlp_all_layers(mlp: 'MLP', inputs: 'fnp.ndarray') -> 'List[fnp.ndarray]'
Forward pass returning activations after each layer.

Args:
    mlp: MLP to execute.
    inputs: Input matrix of shape ``(samples, mlp.width)``.

Returns:
    List of ``depth`` arrays, each shape ``(samples, mlp.width)``.