About training results #72

New Issue

2021-07-27T11:04:04+02:00

alan525 commented

2021-07-27 11:04:04 +02:00

(Migrated from github.com)

I trained the model on my own data and adopted the loss function consistent with the paper. The loss function was stable soon, but the generated pictures were not good. I wonder whether this result is normal and whether it needs to be trained for a long time.

I trained the model on my own data and adopted the loss function consistent with the paper. The loss function was stable soon, but the generated pictures were not good. I wonder whether this result is normal and whether it needs to be trained for a long time. ![image2](https://user-images.githubusercontent.com/17896521/127125495-b693d2fe-9b17-4478-9739-7f0f346f07ec.png)

👀 4

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#72