-
Notifications
You must be signed in to change notification settings - Fork 148
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
Gr = obj_factory(checkpoint['arch']).to(device) KeyError: 'arch' #159
Comments
Oh, you need to add the 'arch' attribute to the checkpoint file. |
File "/data/dev/projects/fsgan/train_inpainting.py", line 266, in main train_inpainting.py", line 266, in main -> Gc_path = os.path.join(checkpoint_dir, 'Gc_latest.pth') But,I'm Got (D_best.pth,D_latest.pth,G_best.pth,G_latest.pth) from training face reenactment. |
Im solved it . |
I'm trying to copy with provided reenactment model(ijbc_msrunet_reenactment_attr_no_seg.py,train_reenactment_attr.py,train_blending.py). After trying the training face reenactment script, the weights created were copied to the swapping folder.When I tried the next step, Training face blending, I got this error. |
I am following Training face inpainting.
How to solve Gr = obj_factory(checkpoint['arch']).to(device) KeyError: 'arch'
I also wrote the reenactment_model location correctly. @YuvalNirkin
The text was updated successfully, but these errors were encountered: