Add faster-coco-eval metric

[MiXaiLL76]

Motivation

Faster COCO Eval

https://github.com/MiXaiLL76/faster_coco_eval

This package wraps a facebook C++ implementation of COCO-eval operations found in the pycocotools package. This implementation greatly speeds up the evaluation time for coco's AP metrics, especially when dealing with a high number of instances in an image.

Modification

I added a variable (use_faster_coco_eval) to the CocoMetric class that allows you to select an additional type of validation, namely COCOeval_faster

Use cases (Optional)

For our use case with a test dataset of 5000 images from the coco val dataset. Testing was carried out using the mmdetection framework and the eval_metric.py script. The indicators are presented below.

Visualization of testing colab_example.ipynb available in directory examples/comparison colab_example.ipynb in google collab Tested with rtmdet model bbox + segm

Summary for 5000 imgs

Type	faster-coco-eval	pycocotools	Profit
bbox	5.812	22.72	3.909
segm	7.413	24.434	3.296

Checklist

1. [x] Pre-commit or other linting tools are used to fix the potential lint issues.

mixaill76@HOME-SERVER:~/mmdetection$ pre-commit run --all-files
flake8...................................................................Passed
isort....................................................................Passed
yapf.....................................................................Passed
trim trailing whitespace.................................................Passed
check yaml...............................................................Passed
fix end of files.........................................................Passed
fix requirements.txt.....................................................Passed
fix double quoted strings................................................Passed
check for merge conflicts................................................Passed
fix python encoding pragma...............................................Passed
mixed line ending........................................................Passed
codespell................................................................Passed
mdformat.................................................................Passed
docformatter.............................................................Passed
check algorithm readme...................................................Passed
check copyright..........................................................Passed

2. [x] The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.

mixaill76@HOME-SERVER:~/mmdetection$ python3 -m coverage run --branch --source mmdet -m pytest tests/test_evaluation/test_metrics/test_coco_metric.py 
========================= test session starts ==========================
platform linux -- Python 3.10.12, pytest-7.4.3, pluggy-1.3.0
rootdir: /home/mixaill76/mmdetection
configfile: pytest.ini
plugins: xdoctest-1.1.4, anyio-3.7.1
collected 17 items                                                                                                                                                                                                                                                             

tests/test_evaluation/test_metrics/test_coco_metric.py ................. [100%]

tests/test_evaluation/test_metrics/test_coco_metric.py::TestCocoMetric::test_evaluate_0
  /usr/lib/python3.10/tempfile.py:999: ResourceWarning: Implicitly cleaning up <TemporaryDirectory '/tmp/tmp606joo9e'>
    _warnings.warn(warn_message, ResourceWarning)

tests/test_evaluation/test_metrics/test_coco_metric.py::TestCocoMetric::test_evaluate_1
  /usr/lib/python3.10/tempfile.py:999: ResourceWarning: Implicitly cleaning up <TemporaryDirectory '/tmp/tmpcnbtqpk6'>
    _warnings.warn(warn_message, ResourceWarning)

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
==================== 17 passed, 2 warnings in 3.47s ====================

3. [x] The documentation has been modified accordingly, like docstring or example tutorials.

[MiXaiLL76]

@BIGWangYuDong Hello! I'm waiting for you Yudong Wang

[vansprosk8]

Good library to speed up calculations

[BIGWangYuDong]

LGTM, kindly ping @hhaAndroid have a look

[MiXaiLL76]

Hello @hhaAndroid, I see that you are active on the site, please take a look at this PR

[MiXaiLL76]

@RangiLyu Maybe you’re here and the project hasn’t been abandoned yet?