New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Too much time cost #21

Closed

nothingeasy opened this issue Sep 10, 2020 · 1 comment

nothingeasy commented Sep 10, 2020

It slower than before too many times when I use this sampler

(self.indices[i] for i in torch.multinomial(self.weights, self.num_samples, replacement=True))
it seems that this expression cost too much time!

Any one have any solution?

www516717402 commented Sep 29, 2020 •

edited

@nothingeasy
In my view, for function is surplus. Modify as follow:

return iter(torch.multinomial(self.weights, self.num_samples, replacement=True).tolist())

I test this modify currently(Not comfirm correct)

This was referenced May 29, 2021

Reduce time for handling large imbalanced dataset #28

Closed

reduce the time when calling sampler #29

Merged

ufoym closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment