Immich machine learning crashes/constantly restarts on RPI 4 with error code 132
Hello, wanted to ask about the issue https://github.com/immich-app/immich/issues/2378
The issue referenced in the comment is seemingly fixed, though my setup has the same problem, aka immich-machine-learning constantly restarts without producing any logs, only the error code 132. My system is Ubuntu 22.04 64bit on RPI 4.
Is there something I'm missing? Is there maybe a beta version that fixes this issue?
GitHub
[BUG] machine learning exists with code 132 · Issue #2378 · immich-...
The bug machine-learning container always exits with code 132 The OS that Immich Server is running on Official Helm chart within k3s (kubernetes) inside systemd-nspawn container inside qemu VM (8.0...
3 Replies
I think the root cause and fix was in the pytorch library (upstream). In a subsequent immich release it should use the new version, and at that point it should be fixed.
Alright, so I just have to wait for the next release? Thanks!
I'm not 100% sure what version of the library gets installed (1.x vs 2.x). We just do pip install pytorch I think.
If it's 2.x then I think it would be included in the next build.