`neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul`

Quantize MatMul.

Module Contents

Classes

FuseNodeStartWithMatmul

Quantize MatMul and apply the fusion.

class neural_compressor.tensorflow.quantization.utils.quantize_graph.quantize_graph_matmul.FuseNodeStartWithMatmul(**kwargs)[source]: Quantize MatMul and apply the fusion.