syna.models.models module

Model utilities and common model classes.

Provides a Model base class (a Layer with plotting helpers) and a simple MLP implementation used in examples and tests.

class syna.models.models.MLP(fc_output_sizes, activation=<function sigmoid>)

Bases: Model

Simple multi-layer perceptron.

Args:

fc_output_sizes (iterable[int]): Sizes for successive Linear layers. activation (callable): Activation applied between layers (not after

the final layer). Defaults to F.sigmoid.

forward(x)

Forward pass: apply activation after every layer except the last.

class syna.models.models.Model

Bases: Layer

Base model class (also a Layer) with a convenience plot method.

The plot method runs forward on the provided inputs and writes a DOT graph of the computation to the given file.

plot(*inputs, to_file='model.png') → None

Run forward and save a DOT graph of the output computation.