-
Notifications
You must be signed in to change notification settings - Fork 31
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
Not able to reproduce the results #9
Comments
Hi, thanks for your attention. |
Hi, I'm also working on reproducing the ResNet-50 based result. python -u main.py Then I fine-tuned it on Youtube-VIS following r50_seqformer_ablation.sh and got a 42.1 mAP, which is about ~3% mAP lower than the 45.1 mAP reported on the ablation model zoo, could you help point out the difference between my pretraining setting to yours? |
Congrats for the awesome work.
I am trying to reproduce the results for resnet-50 backbone.
I tried following ,
Still I am not able to generate the desired numbers.
Can you please help me out with this ?
Thanks,
The text was updated successfully, but these errors were encountered: