torch.ao.quantization.observer.default_weight_observer

torch.ao.quantization.observer.default_weight_observer = functools.partial(<class 'torch.ao.quantization.observer.MinMaxObserver'>, dtype=torch.qint8, qscheme=torch.per_tensor_symmetric){}

Default weight observer.

上一页

torch.ao.quantization.observer.default_placeholder_observer

下一页

torch.ao.quantization.observer.default_reuse_input_observer