autocast.decoders.identity

autocast.decoders.identity#

class IdentityDecoder(in_channels)[source]#

Bases: Decoder

Identity decoder that returns the input as output.

Parameters:

in_channels (int)

decode(z)[source]#

Decode the latent tensor back to the original space.

Parameters:

z (Float[Tensor, 'batch *optional_dims channel']) – Latent tensor to be decoded.

Returns:

Decoded tensor in the original space.

Return type:

Float[Tensor, ‘batch time spatial *spatial channel’]