`numpy.random.choice` to pytorch?
ducha-aiki opened this issue · 6 comments
Hi,
I have quickly checked the possibility to strip out training code and integrate the bare DKM into kornia.
It seems that the main blocker is numpy.random.choice
Line 585 in b3311e2
And the Pytorch doesn't have it
pytorch/pytorch#16897
Is there a way we can use existing pytorch functionality to get a similar thing?
torch.multinomial(certainty, num_samples = min(expansion_factor*num, len(certainty)), replacement=False)Seems like a good option
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.
Could you please check if that works? And, btw, DKM is very welcomed in the shortly upcoming Image Matching Challenge 2023 (CVPR & Kaggle)
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?
@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.