src.model.deeplearn.layer.torf_cast_float_layer

Classes

TORFCastFloatLayer(*args, **kwargs)

class src.model.deeplearn.layer.torf_cast_float_layer.TORFCastFloatLayer(*args, **kwargs)

Author:

Alberto M. Esmoris Pena

Cast an input tensor to float32.

This layer replaces the Lambda wrapper used in the TransfOctoRF architecture to cast boolean masks to float tensors.

\[f(\mathbf{x}) = \operatorname{cast}(\mathbf{x},\;\texttt{float32})\]

__init__(**kwargs)

See Layer and Layer.__init__().

call(inputs, training=False, mask=False)

Cast the input tensor to float32.

Parameters:

inputs – The input tensor.

Returns:

The float32 tensor.

get_config()

Return necessary data to deserialize the layer.

classmethod from_config(config)

Use given config data to deserialize the layer.