qat_config Module¶

TrainingMethod¶

In order to select a training method, please visit the trainable_infrastructure API.

QATConfig¶

Class to configure the quantization process of the model when quantizing using Quantization-aware Training (QAT):

class model_compression_toolkit.qat.QATConfig(weight_training_method=TrainingMethod.STE, activation_training_method=TrainingMethod.STE, weight_quantizer_params_override=None, activation_quantizer_params_override=None)¶

QAT configuration class.

Parameters:

• weight_training_method (TrainingMethod) – Training method for weight quantizers

• activation_training_method (TrainingMethod) – Training method for activation quantizers:

• weight_quantizer_params_override – A dictionary of parameters to override in weight quantization quantizer instantiation. Defaults to None (no parameters)

• activation_quantizer_params_override – A dictionary of parameters to override in activation quantization quantizer instantiation. Defaults to None (no parameters)