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

bottleneck training added #95

Merged
merged 2 commits into from
Jun 10, 2018
Merged

bottleneck training added #95

merged 2 commits into from
Jun 10, 2018

Conversation

stefanbo92
Copy link
Contributor

This pull request adds a training with bottleneck features. With it the training of the last three layers (frozen model) is about 30 times faster and finetuning can even be performed on a CPU in reasonable time.

@qqwweee
Copy link
Owner

qqwweee commented Jun 9, 2018

Thanks for sharing. The idea is refreshing.
Could you delete the part of tiny-yolo3 in case of misunderstanding? And rearrange README. Then I can merge easily.

@stefanbo92
Copy link
Contributor Author

ok, I removed the tiny version from train_bottleneck.py and adjusted the readme!

@qqwweee qqwweee merged commit 998d70d into qqwweee:master Jun 10, 2018
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
@stefanbo92 @qqwweee