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.

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

fix comment in DetectionTargetLayer #962

Merged
merged 4 commits into from
Sep 28, 2018

Conversation

keineahnung2345
Copy link
Contributor

No description provided.

Copy link
Collaborator

@waleedka waleedka left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! All changes look good to me, except the gt_masks shape.

mrcnn/model.py Outdated
@@ -576,7 +575,7 @@ def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config)
deltas /= config.BBOX_STD_DEV

# Assign positive ROIs to GT masks
# Permute masks to [N, height, width, 1]
# Permute masks to [MAX_GT_INSTANCES, height, width, 1]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

gt_masks gets filtered above, so by the time you get to this point, N != MAX_GT_INSTANCES.

@keineahnung2345
Copy link
Contributor Author

@waleedka I have changed it back to N.

@waleedka waleedka merged commit d16c463 into matterport:master Sep 28, 2018
Cpruce pushed a commit to Cpruce/Mask_RCNN that referenced this pull request Jan 17, 2019
* fix comment in DetectionTargetLayer
* fix comment of target_deltas' shape
* make parenthesis compatible
aneeshchauhan pushed a commit to aneeshchauhan/Mask_RCNN that referenced this pull request Jul 9, 2019
* fix comment in DetectionTargetLayer
* fix comment of target_deltas' shape
* make parenthesis compatible
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