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

Hi cadene,why i get this error when i use demo? #34

Open

Rechardgu opened this issue May 2, 2018 · 1 comment

Rechardgu commented May 2, 2018

RuntimeError: softmax(): argument 'input' (position 1) must be Variable, not torch.FloatTensor

Owner

Cadene commented May 2, 2018 •

edited

Loading

It depends on the version of torch you are using (it's fixed with the last version 0.4):

You should add this to hack it:

softmax(torch.autograd.Variable(input, requires_grad=False))

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