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

I can't reproduce dfad results #628

Open
c122-ode opened this issue Feb 27, 2024 · 0 comments
Open

I can't reproduce dfad results #628

c122-ode opened this issue Feb 27, 2024 · 0 comments

Comments

@c122-ode
Copy link

c122-ode commented Feb 27, 2024

I can't reproduce dfad results. my Reproducible results Acc: 87.12 (the results in readme is 92.80)

related information

  1. The output of pip list | grep "mmcv\|mmrazor\|^torch"
    mmcv 2.1.0
    mmrazor 1.0.0
    torch 1.10.0a0+ecc3718

  2. i change mmcls to mmpretrain in the config file
    ./configs/distill/mmcls/dfad/dfad_logits_resnet34_resnet18_8xb32_cifar10.py

  3. i train the model using the below command
    CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 PORT=29547 bash tools/dist_train.sh ./configs/distill/mmcls/dfad/dfad_logits_resnet34_resnet18_8xb32_cifar10.py

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