torch.ao.quantization.stubs.QuantStub#
- class torch.ao.quantization.stubs.QuantStub(qconfig=None)[源代码]#
Quantize stub module, before calibration, this is same as an observer, it will be swapped as nnq.Quantize in convert.
- 参数
qconfig – quantization configuration for the tensor, if qconfig is not provided, we will get qconfig from parent modules