Open talenz opened 3 years ago
I train Resnet18 a4w4 with the following command with the latest repo:
python main.py -a resnet18 --bit 4 --gpu 0 -b 256
The best top1 acc is only 69.01, why it is 1.7% lower (70.7) than the result reported in the paper?
I train Resnet18 a4w4 with the following command with the latest repo:
python main.py -a resnet18 --bit 4 --gpu 0 -b 256
The best top1 acc is only 69.01, why it is 1.7% lower (70.7) than the result reported in the paper?