-
Notifications
You must be signed in to change notification settings - Fork 12
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
Usage error #3
Comments
Hi jxxtin, |
I meet this problem too, and I download the ckpt again, the problem also exist. My solution is: "model.load_state_dict(torch.load(ckpt_path, map_location=model.device)['state_dict'], False)", I'm not sure if this is a side-effect solution, but it does ignore the problem. |
It may have a side-effect. I met the same problem as @jxxtin when running 'python -m src.trainer --opts src/models/omages64_DiT/cfgs/pipeline_N2G2M.yaml --gpus 0 --mode 'test'' and solve it by "model.load_state_dict(torch.load(ckpt_path, map_location=model.device)['state_dict'], False)". However, after running for a while, the following error occurred. Read blend: "/data07/efs/efs-huanan-intern/y84399491/omages/xgutils/assets/preset_glb.blend" 12%|################8 | 1/8 [02:19<16:18, 139.74s/it]Failed to visualize index 1 Failed to visualize index 2 Failed to visualize index 3 Failed to visualize index 4 Failed to visualize index 5 Failed to visualize index 6 Failed to visualize index 7 100%|########################################################################################################################################| 8/8 [02:19<00:00, 17.47s/it] Could you please look into it @QhelDIV? Thank you. |
Hello,
I downloaded the pre-trained script using
python setup/download_ckpts.py
.when I tried to run the sampling code with the following command:
python -m src.trainer --opts src/models/omages64_DiT/cfgs/pipeline_N2G2M.yaml --gpus 0 --mode 'test'
I got the following error
Could you please provide some guidance on how to resolve this?
The text was updated successfully, but these errors were encountered: