neural_compressor.experimental.mixed_precision

Class for low precision model generation across multiple framework backends.

Module Contents

Classes

MixedPrecision

Class used for generating low precision model.

class neural_compressor.experimental.mixed_precision.MixedPrecision(conf_fname_or_obj=None)[source]

Class used for generating low precision model.

MixedPrecision class automatically generates low precision model across various DL frameworks including tensorflow, pytorch and onnxruntime.