tensorplay.ao.quantization.fake_quantize_per_channel

tensorplay.ao.quantization.fake_quantize_per_channel(x, scales, zero_points, axis=0, quant_min=-128, quant_max=127)[source]

Applies per-channel fake quantization with fixed affine parameters.

Gradient passes through where x lies inside its channel’s representable real range [qmin-zp, qmax-zp]*scale, else zero.