tensorflow / tensorflow/models

one question about filtering anchors by area (<0) in faster rcnn net

Open
#6,486 2 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Jul 1, 2020.

models:research:odapi type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
No merged PRs in 30d

Description

https://github.com/tensorflow/models/blob/8e7051a8c1c4069f004a072362b173e70a8e260a/research/object_detection/meta_architectures/faster_rcnn_meta_arch.py#L664

here is my question:
If we can filter anchors by area (<0) in clip_to_window function , how we can match dimensions between anchors and rpn_box_encodings (or rpn_objectness_predictions_with_background)。I think that dimensions of anchors is [boxNum,4] ,rpn_box_encodings is [?，boxNum,4] , but if we filter anchors by area < 0 , anchors.shape[0] may not equal to boxNum.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.