build

open override fun build(tf: Ops, input: Operand<Float>, isTraining: Operand<Boolean>, numberOfLosses: Operand<Float>?): Operand<Float>

Extend this function to define variables in the layer and compute layer output.

Parameters

tf

TensorFlow graph API for building operations.

input

Layer input.

isTraining

TensorFlow operand for switching between training and inference modes.

numberOfLosses

TensorFlow operand for batch size data.

open override fun build(tf: Ops, input: List<Operand<Float>>, isTraining: Operand<Boolean>, numberOfLosses: Operand<Float>?): Operand<Float>

Extend this function to define variables in the layer and compute layer output.

NOTE: This function should be overridden for layers with multiple inputs. NOTE: Used in Functional API

Parameters

input

Layer input list.

isTraining

TensorFlow operand for switching between training and inference modes.

numberOfLosses

TensorFlow operand for batch size data.