tensorflow / tensorflow/models

Format bboxes - exporting tflite graphs

Open
#10,500 0 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Feb 17, 2022.

models:research:odapi type:bug
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

If I am not mistaken this docstring (https://github.com/tensorflow/models/blob/9c8cbd0ce88a59565369934c5e3e7ca688302a7f/research/object_detection/export_tflite_graph_lib_tf2.py#L160) is not correct, the image input would not be a float32 tensor of shape [num_anchors, 4] containing the anchor boxes but a float32 tensor of shape model_input_size containing the image we are doing inference over.

Moreover, I would like to know the format of the output boxes, which coordinates are used in this case?

Thank you for reading.

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.