Module providing Consciousness Exploration Tools for PyTorch.

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the gallery for the big picture.

class consciousnet.losses.TDVAELoss(obs_loss=None)[source]¶

TDVAE Loss function.

This loss needs intermediate layers outputs. Use a callback function to set the ‘layer_outputs’ class parameter before each evaluation of the loss function. If you use an interface this parameter is updated automatically.

__init__(obs_loss=None)[source]¶: Initialize self. See help(type(self)) for accurate signature.

Examples¶

Jumpy prediction with Temporal Difference Variational Auto-Encoder (TD-VAE)¶