Base class of quantized-float related Module, basically for QAT and Calibration.
Use from_float_module to generate a instance from float Module.
Or use quantize_qat to do it recursively and automatically.
Can also be converted to QuantizedModule for deployment using
quantize further.
-
apply_quant_activation(target)[source]
Apply weight’s observer and fake_quant from qconfig on target.
-
apply_quant_bias(target, inp, w_qat)[source]
Use fake_quant_bias to process target. Only valid when
act_fake_quant and weight_fake_quant are both enabled.
-
apply_quant_weight(target)[source]
Apply weight’s observer and fake_quant from qconfig on target.
-
abstract classmethod from_float_module(float_module)[source]
Return a QATModule instance converted from
a float Module instance.
-
get_activation_dtype()[source]
Get activation’s quantization dtype as the method from qconfig.
-
get_activation_qparams()[source]
Get activation’s quantization parameters.
-
get_weight_dtype()[source]
Get weight’s quantization dtype as the method from qconfig.
-
get_weight_qparams()[source]
Get weight’s quantization parameters.
-
set_qconfig(qconfig)[source]
Set quantization related configs with qconfig, including
observer and fake_quant for weight and activation.