Page 1 of 1

Caught exception in thread: '_training_0'

Posted: Sat Jul 11, 2020 4:38 pm
by DutchMex

Hi Faceswap Community,
I am relatively new here (only been experimenting with this software for a few months). I have been training a model for a while, then gave it a break. When I came back to it, even after updating, it always crashes. I have tried to add photos to give the model more to work with, and made sure that they are all the same size when extracted. I have tried different models as well and all of them seem to crash the same way. Ideally I want to use Villain or realface. At best I can only get the system to run one cycle before crashing.

PC Hardware:
GPU: RTX 2070 Super
CPU: Intel i7 9700
RAM: 16 GB

(sorry I don't know how to make the log look nice so I linked to it on gitlab)
Log:
https://gitlab.com/CmdQue/faceswap-file ... .gitignore


Re: Caught exception in thread: '_training_0'

Posted: Sun Jul 12, 2020 9:40 am
by torzdf

Unfortunately the Memory Saving Gradients has pushed the useful information off the log.

However, this error usually occurs when the training images are not all the same size, so I would start with checking that.