Search found 9 matches
- Tue Apr 19, 2022 11:32 am
- Forum: Convert Discussion
- Topic: Black spots on swapped face
- Replies: 3
- Views: 7037
Re: Black spots on swapped face
I have had similar outcome in two cases, both my own fault: 1) the training dataset had consistent masking issue where obstructed part of face was still masked as part of face. Eg. if the face had a hat, that had cast a shadow to forehead. The shadow was so consistently present that it became part o...
- Tue Apr 19, 2022 6:15 am
- Forum: Extract Support
- Topic: Exclude GPU has wrong device IDs
- Replies: 2
- Views: 1021
Re: Exclude GPU has wrong device IDs
Looking at the logs, there appears to be something else mixed up. Configuration in faceswap: ID 0 = 2060 <-- excluded with checkbox ID 1 = 2080Ti It starts by checking the free memory of 2080Ti. But then tensorflow puts the job on to ID 0, that is 2060. Checking the memory consumption and utilizatio...
- Mon Apr 18, 2022 6:31 am
- Forum: Extract Support
- Topic: Exclude GPU has wrong device IDs
- Replies: 2
- Views: 1021
Exclude GPU has wrong device IDs
Hello, when using "Exclude GPU" checkboxes, you can see the GPU name when hovering mouse over the checkbox. However it appears that the GPU IDs those checkboxes indicate, are wrong. Example: I have two GPUs, 2060S and 2080Ti. I wish to exclude 2060S to extract using 2080Ti. The checkbox in...
- Sun Jan 16, 2022 2:35 pm
- Forum: General Discussion
- Topic: Select specific GPU to use.
- Replies: 1
- Views: 1425
Re: Select specific GPU to use.
The argument is -X for excluding GPUs. For example, putting argument -X 0 1 will exclude GPU:0 and GPU:1 I use it for forcing to make operations with specific GPU or even CPU-only, while the other GPU is already training some other stuff in other console (if you want to do parallel work like this, y...
- Thu Jan 06, 2022 1:35 pm
- Forum: Training Support
- Topic: You have selected eye/mouth loss multipliers greater than 1x, but Penalized Mask Loss is disabled. Disabling all multipl
- Replies: 2
- Views: 1332
Re: You have selected eye/mouth loss multipliers greater than 1x, but Penalized Mask Loss is disabled. Disabling all mul
That error may happen, if you have added a new alignment / face using the manual tool and then done extraction from alignment file. And that face does not have a mask in bisenet-fp_face type, it just has the two default ones... while rest of the files have that mask. You have two options, if above i...
- Thu Nov 18, 2021 6:46 pm
- Forum: Training Support
- Topic: Transfer learning (load weights) fails with same model
- Replies: 7
- Views: 7680
Re: Transfer learning (load weights) fails with same model
Thank you, it is working brilliantly! =)
- Wed Nov 10, 2021 6:38 pm
- Forum: Training Support
- Topic: Transfer learning (load weights) fails with same model
- Replies: 7
- Views: 7680
Re: Transfer learning (load weights) fails with same model
Hi, yes, thank you for quick action. I was able to get it working by starting training with the transfer learning. It then crashed to 1 iteration as described in the other thread. But when I made copies of the generated 1 iteration model and its json, renamed them to old filenames, then it could pro...
- Mon Nov 08, 2021 3:27 pm
- Forum: Training Support
- Topic: Transfer learning (load weights) fails with same model
- Replies: 7
- Views: 7680
Re: Transfer learning (load weights) fails with same model
Hi, thanks for quick reply. The model file is pretty large, over 2GB h5 file, and does not zip much smaller. I'll try if I can reproduce the issue with smaller config. Here is the dfl_sae_state.json , I am not sure if it is helpful. { "name": "dfl_sae", "sessions": { &q...
- Mon Nov 08, 2021 10:08 am
- Forum: Training Support
- Topic: Transfer learning (load weights) fails with same model
- Replies: 7
- Views: 7680
Transfer learning (load weights) fails with same model
Hello, after training a model very far using faces A to B, I wished to see if I could give a boost for C to B with transfer learning. I loaded the project of A to B, and only changed the input from A to C and the model directory. Then I set the Load Weights to point the model directory of A to B. Th...