LinearAEEncoder

class behavenet.models.aes.LinearAEEncoder(n_latents, input_size)[source]

Bases: BaseModule

Linear encoder.

Methods Summary

build_model()

Construct the encoder.

forward(x[, dataset])

Process input data.

Methods Documentation

build_model()[source]

Construct the encoder.

forward(x, dataset=None)[source]

Process input data.

Parameters:

  • x (torch.Tensor object) – input data

  • dataset (int) – used with session-specific io layers

Returns:

  • encoder output (torch.Tensor): shape (n_latents)

  • NoneType: to match convolutional encoder outputs

  • NoneType: to match convolutional encoder outputs

Return type:

tuple