Skip to content

Conversation

elliottzheng
Copy link
Contributor

@elliottzheng elliottzheng commented Jun 2, 2018

Running test in pytorch 0.4 , the accurary is always zero, because we need to transform zero dimensional tensor to python number by .item(), so I made a small fix.

@fxia22 fxia22 merged commit 75dd61c into fxia22:master Jun 2, 2018
@fxia22
Copy link
Owner

fxia22 commented Jun 2, 2018

thanks a lot, by the way, are you able to use nndistance module in 0.4? Some users report that there is out of memory error.

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.

2 participants