megengine.quantization.fake_quant_tensor

fake_quant_tensor(inp, qparams)[source]

Apply fake quantization to the inp tensor.

Parameters

  • inp (Tensor) – the input tensor which need to be faked.

  • qparams (QParams) – to get mode, qmin, qmax, scale and zero_point from.

Return type

Tensor

previous

megengine.quantization.fake_quant_bias

next

megengine.traced_module