onnx / onnx/models

MaskRCNN model inference labelid do not match to coco gt annotation

Open
#602 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Ask a Question

Hi,
I am trying to get mAP for COCO val 2017 dataset with this model MaskRCNN-12-int8.onnx.
But, the category id does not match between the output and the gt annotations instances_val2017.json.
For example, image 00000397133.jpg has some spoons that model gives id 46, but in annotations is id 50.

Question

What am I doing wrong?

Further information

Ubuntu 22.04
Python 3.10
onnxruntime 1.14.1

Is this issue related to a specific model?
Model name: MaskRCNN-12-int8.onnx
Dataset: coco_val2017

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Reproduce the MaskRCNN-12-int8.onnx inference on the COCO val 2017 example image 00000397133.jpg and compare its category IDs with instances_val2017.json. Determine whether the mismatch is specific to this model or reflects a category-mapping issue, then document the finding and the correct basis for computing mAP.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.