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

Refine the doc in detection_output API. #8689

Merged
merged 3 commits into from
Mar 5, 2018

Conversation

qingqing01
Copy link
Contributor

Fix #8685

This layer applies the NMS to the output of network and computes the
predict bounding box location. The output's shape of this layer could
be zero if there is no valid bounding box.
This operation decode the predicted bboxes according to the prior bboxes
Copy link
Collaborator

Choose a reason for hiding this comment

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

This operation updates bounding boxes by applying multi-class non-maximum suppression (NMS) and re-scoring.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Re-write the doc. Thanks!

@@ -91,7 +92,14 @@ class number, M is number of bounding boxes. For each category
nms_eta(float): The parameter for adaptive NMS.

Returns:
The detected bounding boxes which are a Tensor.
Variable: The detection outputs which is a LoDTensor with shape [No, 6].
Copy link
Collaborator

Choose a reason for hiding this comment

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

There should be a comma (,) before "which".

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Re-write the doc. Thanks!

@@ -91,7 +92,14 @@ class number, M is number of bounding boxes. For each category
nms_eta(float): The parameter for adaptive NMS.

Returns:
The detected bounding boxes which are a Tensor.
Variable: The detection outputs which is a LoDTensor with shape [No, 6].
Each row has 6 values: [label, confidence, xmin, ymin, xmax, ymax],
Copy link
Collaborator

Choose a reason for hiding this comment

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

Use six instead 6.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done. Thanks!

offset is N + 1, N is the batch size. If LoD[i + 1] - LoD[i] == 0,
means there is no detected bboxes for for i-th image. If there is
no detected boxes for all images, all the elements in LoD are 0,
and the Out only contains one value which is -1.
Copy link
Collaborator

Choose a reason for hiding this comment

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

the Out => Out

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Re-write the doc. Thanks!

@qingqing01 qingqing01 requested a review from pkuyym March 2, 2018 02:24
Copy link
Contributor

@chengduoZH chengduoZH left a comment

Choose a reason for hiding this comment

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

LGTM

@qingqing01 qingqing01 merged commit bbf98a0 into PaddlePaddle:develop Mar 5, 2018
@qingqing01 qingqing01 deleted the ssd_api branch March 7, 2018 12:02
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.

None yet

3 participants