default_activation_only_qconfig¶
- torch.quantization.qconfig.default_activation_only_qconfig¶
alias of QConfig(activation=functools.partial(<class ‘torch.ao.quantization.fake_quantize.FakeQuantize’>, observer=<class ‘torch.ao.quantization.observer.MovingAverageMinMaxObserver’>, quant_min=0, quant_max=255, dtype=torch.quint8, qscheme=torch.per_tensor_affine, reduce_range=True){}, weight=<class ‘torch.nn.modules.linear.Identity’>)
