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.

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

Fix iter_size support with cuDNN convolution #96

Merged
merged 1 commit into from
Aug 4, 2016
Merged

Fix iter_size support with cuDNN convolution #96

merged 1 commit into from
Aug 4, 2016

Conversation

yjxiong
Copy link
Owner

@yjxiong yjxiong commented Aug 4, 2016

@yjxiong yjxiong merged commit c0d200b into action_recog Aug 4, 2016
@yjxiong yjxiong deleted the fix/cudnn_conv branch August 11, 2016 04:00
@antran89
Copy link

@yjxiong Can you explain why the line is a bug? Does BLVC Caffe fix this bug? We are using many different versions of Caffe, and I wonder whether this bug affect our version? Thanks

@yjxiong
Copy link
Owner Author

yjxiong commented Oct 24, 2016 •
edited
Loading

This is a bug and was fixed in last October in the BVLC version.

Zeroing all gradients is done on the solver level. Layers should not zero their gradients. Otherwise, the iter_size param won't work as expected.

@antran89
Copy link

@yjxiong Thank for your explanations.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@yjxiong @antran89