ConvAEEncoder

class behavenet.models.aes.ConvAEEncoder(hparams)

Bases: behavenet.models.base.BaseModule

Convolutional encoder.

Methods Summary

build_model()	Construct the encoder.
forward(x[, dataset])	Process input data.

Methods Documentation

build_model()

Construct the encoder.

forward(x, dataset=None)

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)

• pool_idx (list): max pooling indices for each layer

• output_size (list): output size for each layer

Return type

tuple