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

Problem of Reproducing #12

Open
luck528 opened this issue Mar 12, 2021 · 0 comments
Open

Problem of Reproducing #12

luck528 opened this issue Mar 12, 2021 · 0 comments

Comments

@luck528
Copy link

luck528 commented Mar 12, 2021

Hello,

Thanks for your contribution and work. But I have the problem of reproducing the results:

I use the following command:
python3 tools/solve_gta5.py --gpu "0" --backbone "deeplabv2_multi" --dataset 'cityscapes' --checkpoint_dir "./log/gta2city_AdaptSegNet_ST=0.1_maxsquare_round=5/" --pretrained_ckpt_file "./pretrained_model/GTA5_source.pth" --round_num 5 --target_mode "maxsquare" --freeze_bn False --weight_decay 5e-4 --lr 2.5e-4 --lambda_target 0.1

And I see the INFO:
Checkpoint loaded successfully from ./pretrained_model/GTA5_source.pth

However, I run the experiments for 5 times, but the highest performance I get is only 43.0%, while the reported result is 44.3%.

I am wondering whether some others successfully reproduce the results and whether there are any hints.

@luck528 luck528 changed the title Issues on evaluation and the problem of reproducing Problem of Reproducing Mar 12, 2021
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