`numpy.random.choice` to pytorch? about dkm HOT 6 CLOSED

torch.multinomial(certainty, num_samples = min(expansion_factor*num, len(certainty)), replacement=False)

Seems like a good option

from dkm.

I think the main issue with np.random.choice missing in Pytorch is that you have to pipeline multinomial -> indexing instead of having it as a single function. However, as I'm just using it for indexes here anyway I think there is no major issue.

from dkm.

Could you please check if that works? And, btw, DKM is very welcomed in the shortly upcoming Image Matching Challenge 2023 (CVPR & Kaggle)

from dkm.

Sure, I'll check, and we'll provide a DKM baseline kernel to run for IMC. By the way @ducha-aiki, is Kaggle python 3.7 only? e.g. PyTorch 2.0 doesn't seem to have any binaries for cp37?

from dkm.

@Parskatt well, I more meant to take part and win the challenge :)
Regarding Python 3.7 - kaggle kernel is 3.7 only now, but given the EOL soon, we can safely bet they will upgrade in month or two.

from dkm.

Multinomial seems fine, should be in here #22 .

from dkm.