quantize#

classtorch.ao.quantization.quantize(model,run_fn,run_args,mapping=None,inplace=False)[source]#

Quantize the input float model with post training static quantization.

First it will prepare the model for calibration, then it callsrun_fn which will run the calibration step, after that we willconvert the model to a quantized model.

Parameters

• model – input float model

• run_fn – a calibration function for calibrating the prepared model

• run_args – positional arguments forrun_fn

• inplace – carry out model transformations in-place, the original module is mutated

• mapping – correspondence between original module types and quantized counterparts

Returns

Quantized model.