torch.ao.quantization.observer.FixedQParamsObserver

class torch.ao.quantization.observer.FixedQParamsObserver(scale, zero_point, dtype=torch.quint8, qscheme=torch.per_tensor_affine, quant_min=0, quant_max=255)

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

参数

• scale (float) – fixed scale for the observer

• zero_point (int) – fixed zero point for the observer

• dtype –

• qscheme –

• quant_min –

• quant_max –

上一页

torch.ao.quantization.observer.HistogramObserver

下一页

torch.ao.quantization.observer.PlaceholderObserver