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.

Sign up for GitHub

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

Can't reproduce results in the paper #10

Open

hungk64it1x opened this issue Mar 13, 2024 · 1 comment

hungk64it1x commented Mar 13, 2024

Hello Huy,

After I tried 3 times to train your model (from scratch or with pretrained model) I couldn't reproduce your score (Kvasir score seems to be got highest ~ 0.90x) sometimes It shows val_loss did not improve from epoch 2 (https://drive.google.com/file/d/1Y881vzx65M2MR0z0Gfd-MoPCPuGrMeml/view?fbclid=IwAR1M1-pNwNNdcmrM8N1IrhGhhl5TsDcuHBHmiObcvgeXwARqgBUetvmwXfk)

I provided the weight I have trained.

Thank you very much.

Owner

huyquoctrinh commented Mar 18, 2024

Hi, thank you so much, I will reproduce your result again

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment