error accuracy
TangKun1234 opened this issue · comments
I download the alexnet model from (https://download.pytorch.org/models/alexnet-owt-4df8aa71.pth) and evaluate the model by the val224_compressed.pkl with quantize.py , but the accuracy only 0.5397. Why?
The default setting will quantize the weights with 8bits and activation with 8bits.