Function quantize

torch/ao/quantization/quantize.py:358–384

r"""Quantize the input float model with post training static quantization. First it will prepare the model for calibration, then it calls `run_fn` which will run the calibration step, after that we will convert the model to a quantized model. Args: model: input float model

(model, run_fn, run_args, mapping=None, inplace=False)

    _remove_activation_post_process(module)

def quantize(model, run_fn, run_args, mapping=None, inplace=False):
    r"""Quantize the input float model with post training static quantization.

    First it will prepare the model for calibration, then it calls
    `run_fn` which will run the calibration step, after that we will
    convert the model to a quantized model.

    Args:
        model: input float model
        run_fn: a calibration function for calibrating the prepared model
        run_args: positional arguments for `run_fn`
        inplace: carry out model transformations in-place, the original module is mutated
        mapping: correspondence between original module types and quantized counterparts

    Return:
        Quantized model.
    """
    torch._C._log_api_usage_once("quantization_api.quantize.quantize")
    if mapping is None:
        mapping = get_default_static_quant_module_mappings()
    if not inplace:
        model = copy.deepcopy(model)
    model.eval()
    prepare(model, inplace=True)
    run_fn(model, *run_args)
    convert(model, mapping, inplace=True)
    return model

def quantize_dynamic(model, qconfig_spec=None, dtype=torch.qint8,
                     mapping=None, inplace=False):