bitwidth of each layer (discussion of MP)

[hustzxd]

Thanks for your great works. I want to know which layers are more sensitive to quantization. I would be very grateful if you can share the (MP4) bit-width of each layer of MobileNet or ResNet.

[hustzxd]

I added the mixed-precision experiments. https://github.com/rhhc/ZeroQ-MP However, there are relatively large accuracy gaps with the results of the paper in some cases. So far, I have done several sets of experiments to compare the effects of quantization hyper-parameter(e.g., percentile). In particular, I only apply the “percentile” quantization to the activations. I would be very grateful if the authors or others can give me some suggestions to improve the results of the experiment

[xiezheng-cs]

Thanks for your great works. I want to know which layers are more sensitive to quantization. I would be very grateful if you can share the (MP4) bit-width of each layer of MobileNet or ResNet.

+1