FixedQParamsFakeQuantize

class torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize(observer) [source]

Simulate quantize and dequantize in training time.

Simulate quantize and dequantize with fixed quantization parameters in training time. Only per tensor quantization is supported.

extra_repr() [source]

Define a string representation of the object’s attributes.