ichu-apl

^ agreed, this dataset looks like it could be very useful.

ah, I'm also experiencing this issue. It looks like something in the super_gradients library is redirecting stdout. ```py print("a") from super_gradients.training import models print("b") print("c", flush=True) crash=crash print("d") print("e", flush=True)...

You can wrap the import with a stored stdout to undo the redirect. ```py import sys stdout = sys.stdout from super_gradients.training import models sys.stdout = stdout ```

This can be fixed by just running the required function, but it lacks documentation. Either this requirement should be dropped, or the pretrained_weights + checkpoint conflict note should be removed...

wait, there isn't a conflict and running model.get() with both checkpoint_path and pretrained_weights solves the issue. This note in `https://github.com/Deci-AI/super-gradients/blob/master/src/super_gradients/training/models/model_factory.py#L225` should be removed: `NOTE: Passing pretrained_weights and checkpoint_path is ill-defined...