Skip to content
This repository has been archived by the owner on Nov 9, 2023. It is now read-only.

XSeg training stops after loading all samples (no errors) #5736

Open
arcvaw opened this issue Oct 10, 2023 · 0 comments
Open

XSeg training stops after loading all samples (no errors) #5736

arcvaw opened this issue Oct 10, 2023 · 0 comments

Comments

@arcvaw
Copy link

arcvaw commented Oct 10, 2023

Expected behavior

Attempting to train XSeg by running 5.XSeg) train.bat after generating masks using the default generic XSeg model.

After the XSeg trainer has loaded samples, it should continue on to the filtering stage and then begin training.

Actual behavior

Instead of the trainer continuing after loading samples, it sits idle doing nothing infinitely like this:

image

There are no errors visibly being logged.

Steps to reproduce

  1. Run 5.XSeg) train.bat
  2. Select NVIDIA GeForce RTX 2080 SUPER GPU
  3. Use whole face type
  4. Use a batch size of 8
  5. Do not enable pretraining mode

Other relevant information

OS: Windows 10
GPU: NVIDIA GeForce RTX 2080 SUPER
CPU: AMD Ryzen 9 3900X
RAM: 16GB

I've tried modifying virtual ram and changing drivers.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant