pub const NNQuantizationType_NNQuantizationType_Affine_PerChannel: NNQuantizationType = 2;Expand description
Affine quantization with separate parameters applied to each channel. Also known as per-axis where the axis is always the channel “C” axis in a NCHW, NHWC, and so-on shaped tensor.
Same equation as @ref NNQuantization_Affine_PerTensor but applied per-channel. The scale and zero_point are vectors of channel length.