Please update the unfair comparison with ShiftAddNet
ranery opened this issue · comments
Haoran You commented
Hi,
We recently noticed that you update the comparison with ShiftAddNet in your readme.
However, the chosen accuracy of ShiftAddNet (i.e., 85.10%) is wrongly from our adaption experiments, for which we only use half the CIFAR-10 dataset to pre-train. Our accuracy (ResNet-20 on CIFAR-10) should be 89.32%, which is also trained with a different setting and different implementation (e.g., only 160 epochs).
Could you help to update the comparison results?
Best regards,
Haoran You
HantingChen commented
Sorry for the mistake. The results have been updated.
Haoran You commented
Thanks!