Skip to content

Problem of Reproducing #12

Description

@luck528

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.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions