Window Data Layer for Detection Finetuning#245
Merged
Conversation
matlab/caffe/matcaffe.cpp
Outdated
Member
Author
There was a problem hiding this comment.
@rbgirshick to the best of my knowledge this was just an out-of-date comment, but please check for me.
Merged
Contributor
|
Just read through the code - all looks good to me. I'll compile and test the updated matcaffe wrapper too. |
this commit (in addition to all caffe unit tests passing)
Contributor
|
Just tested the matcaffe wrapper and that everything matches up in the RCNN system - computed features are identical to previously computed ones. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is my integration of the window data layer authored by Ross Girshick as part of R-CNN [1]. This data layer is useful for the finetuning of detectors by training on window crops instead of whole images.
This change was meant for release 0.99 and will be retroactively added to the release once merged.
[1] Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. Arxiv 2013.