search

jakc4103 / DFQ

PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.
MIT License
258 stars 45 forks source link

working with 6 bits show gap w.r.t the original paper #31

Closed nsping13 closed 3 years ago

nsping13 commented 3 years ago

Hi, thanks a lot for the great work you have done here. For ResNet18 the author of the paper wrote that the accuracy is 66.3% while here we get 58%, do you have any idea what the reason is Thanks a lot :)

jakc4103 commented 3 years ago

I'm not quite sure the exact reason, might related to different implementation of quantization and equalization procedures.