Deep Sea

I also saw same result. Dice was 0.01 and and see too man "nan" at the result.

Sorry, Dataset was about teeth segmentation. Label is like as follow: 0: background 1~16: upper teeth 17~32: lower teeth. This is just instance segmentation project. But unfortunately, nnUNet was just...

Already done.(CBCT teeth segmentation) But couldn't get any good idea.

Also problem is that teeth order is different in every images.

I also met same problem. I checked unique values in output json flle. The labels were like this: {0, 11, 12, 13, 14, 15, 16, 17, 21, 22, 23, 24,...

Hello. I analyzed eval_visualize_results.py source code. There was an logical error in get_colored_mesh() function. For example, the teeth label was [0, 11, 12, 13, 14, 15, 16, 17, 21, 22,...

One more. I used this code. ``` import numpy as np from glasses_detector import GlassesSegmenter # Initialize full segmentation model of size large seg_full = GlassesSegmenter(kind='lenses', size='medium') # TODO: change...

Thank you. I'll test with them.

The accuracy is improved a lot. But still some bad samples.     But totally, I think overall accuracy is good. If we add some more dataset, the...