GT boxes: exclude the ones that are iscrowd from COCO #506
Conversation
This file contains 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
|
Please use the v0.12 version right now in case you find any issue, I just
merged from another pull request to update it to tensorflow 1.0, quite a
lot of weights/models may not be there yet.
…---------------------
Ender X. Chen
Language Technologies Institute,
School of Computer Science,
Carnegie Mellon University, Pittsburgh, PA
On Thu, Mar 2, 2017 at 8:13 AM, Xiaoyu Tao ***@***.***> wrote:
@endernewton <https://github.com/endernewton> I'm trying your tensorflow
version of faster r-cnn. It seems there should be some changes when
migrating pycocotools in py-faster-rcnn.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#506 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ACTwEZVD0RpPN2ZxH3ZzRfVoQF-Bjtwhks5rhsCHgaJpZM4MMkhf>
.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
It seems like for the faster RCNN version of the code, the boxes that contain multiple objects ('iscrowd') are still included in the training. I am doing some side experiments to verify whether excluding them will improve performance. Creating this pull request.