Skip to content
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.

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

1. decouple boxes, labels; 2: cast lables to 64 bits #74

Merged
merged 1 commit into from
Sep 14, 2019

Conversation

hyl-g
Copy link

@hyl-g hyl-g commented Sep 13, 2019

As the title said, there are two changes:

  1. Decouple boxes and labels in _getitem() to prevent corruption of dataset.
  2. In _read_data(), cast labels to int16 because cross_entropy() expects torch.LongTensor.

@qfgaohao qfgaohao merged commit 7174f33 into qfgaohao:master Sep 14, 2019
@qfgaohao
Copy link
Owner

@hyl-g Thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants