Timbus Calin

I also mention that the accuracy is very high during the training and the masks are prepared accordingly(tested with other neural network).

30 classes and applying softmax not sigmoid; to the best of my knowledge sigmoid can be applied in case of overlapping classes, just like in multilabel classification.

Will test again with new testing configuration.

I also ran into this issue, maybe we make a mistake at a point during training/inference.

> > > @blaxe05 Hi, > I am sorry, but because of this problem and other problems i didn't use Deeplab. In my case i used Mask R-CNN. So unfortunately...

Same issue with transformers==4.30.2 and ray[tune]==2.51.0

This has been closed by github-actions, but the problem has not been solved ofc ...

@amyeroberts Sure, thank you for the prompt response. So whenever I run a PopulationBasedTraining() with perturbation_interval > 1, I get such an error, exactly like the one mentioned above. `ValueError:...

Same issue