ConvolutionalEncoderDecoder2d

class deeplay.components.cnn.encdec.ConvolutionalEncoderDecoder2d(*args, **kwargs)

Bases: DeeplayModule

Attributes Summary

blocks	Return the blocks of the encoder and decoder.
normalization	Return the normalization layers of the encoder and decoder.
pool	Return the pooling layers of the encoder.
upsample	Return the upsampling layers of the decoder.

Methods Summary

forward(x)

Define the computation performed at every call.

Attributes Documentation

blocks

Return the blocks of the encoder and decoder. Equivalent to .encoder.blocks + .bottleneck.blocks + .decoder.blocks.

normalization

Return the normalization layers of the encoder and decoder. Equivalent to .encoder.normalization + .bottleneck.normalization + .decoder.normalization.

pool

Return the pooling layers of the encoder. Equivalent to .encoder.pool.

upsample

Return the upsampling layers of the decoder. Equivalent to .decoder.upsample.

Methods Documentation

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.