Why do I use the model trained on the 512-cropped data set to make predictions, and the result is so The result is so unsatisfactory? #406

New Issue

2023-05-09T12:00:10+02:00

liaoyunfengs commented

2023-05-09 12:00:10 +02:00

(Migrated from github.com)

I use train.py to train the model, and get the 528000_net_D.pth, 528000_net_G.pth, 528000_optim_D.pth, 528000_opt_G.pth, then use the 528000_net_G.pth to make predictions by test_wholeimage_swapsingle.py. Why is the result of changing faces like this?

![630_0_0](https://user-images.githubusercontent.com/45155977/237062246-b5b55acc-2bc2-4221-9a41-4f1cfb277fe6.jpg) I use train.py to train the model, and get the 528000_net_D.pth, 528000_net_G.pth, 528000_optim_D.pth, 528000_opt_G.pth, then use the 528000_net_G.pth to make predictions by test_wholeimage_swapsingle.py. Why is the result of changing faces like this?

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#406