search

huawei-noah / AdderNet

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"
BSD 3-Clause "New" or "Revised" License
954 stars 187 forks source link

Migrating from a Simple CNN Architecture to AdderNet #71

Closed alarst13 closed 1 year ago

alarst13 commented 1 year ago

Hi. I have a CNN architecture that I trained on CIFAR-10 with and without AdderNet. I could reach an accuracy of over %80 without AdderNet but when I used AdderNet it got stuck at %10 accuracy. Is there anything wrong with my implementation? All I did was to replace nn.conv2D with adder.adder2d. Isn't it supposed to work like this? How do you suggest I should migrate from a simple CNN architecture to AdderNet? Thank you!

alarst13 commented 1 year ago

During the train_test the accuracy stayed the same at %10 for 100 epochs.

alarst13 commented 1 year ago

The problem was that I wasn't using Batch Normalization which we were instructed to use in the paper,