Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

performance of resnet20 on cifar10 #2

Open
JiaxiangRen opened this issue May 26, 2021 · 0 comments
Open

performance of resnet20 on cifar10 #2

JiaxiangRen opened this issue May 26, 2021 · 0 comments

Comments

@JiaxiangRen
Copy link

Hi,

Thanks for releasing the code.
I found out that the performance of resnet20 on cifar10 is not that good.
here is the script I use:
python main.py --config configs/smallscale/resnet18/resnet20-ukn-unsigned.yaml --multigpu 3 --name cifar10_resnet20 --data ../datasets/ --prune-rate 0.5
which achieves only 85% acc on test set.
the strange thing is that when I set the prune_rate to 0.9 which means I keeps more weights compared to 0.5, but I got only 50% acc on test set.
python main.py --config configs/smallscale/resnet18/resnet20-ukn-unsigned.yaml --multigpu 3 --name cifar10_resnet20 --data ../datasets/ --prune-rate 0.9

can you tell me if anything wrong in my script?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant