Soumya Snigdha Kundu
Soumya Snigdha Kundu
 What do the boxes and squares actually indicate?
When I ran this locally with a huge file structures, the previous extraction failed for me. This version is more adept to any file structure.
"The preset are merely there `ot` make life easier". Congrats and Super interesting results in the new paper :)
` python -m medmnist download pneumoniamnist --size=28 ` ends up throwing a root not found error but I remove that and do just `python -m medmnist download --size=28` it seems...
``` File "cc3d.pyx", line 336, in cc3d.connected_components File "cc3d.pyx", line 225, in cc3d.estimate_provisional_labels TypeError: Type float16 not currently supported. ``` Listing what all are the available options would be nice.
`(base) :~/loss/SegLossBias/tests$ python test_compound_losses.py Traceback (most recent call last): File "~/SegLossBias/tests/test_compound_losses.py", line 5, in from seglossbias.modeling.compound_losses import CrossEntropyWithL1, CrossEntropyWithKL ModuleNotFoundError: No module named 'seglossbias' ` I simply cloned and tried...
Maybe a naive question, but -> It becomes a bit tedious detaching and reattaching stuff when this is required within a pipeline. Is there any way this can be done...
I am aware that doing the real validation multiple times is not computationally meaningful. However, I do want to perform it a bit earlier in the training to gauge some...
Why do we need pass bounding box values in the loss? My assumption was that solo does not need any bounding box information?