[Feature]: Support print per class AP.

[RangiLyu]

Support print per class AP

resolve #317
resolve #250
resolve #39

Evaluate annotation type *bbox*
DONE (t=33.63s).
Accumulating evaluation results...
DONE (t=8.08s).
[NanoDet][01-26 20:17:31]INFO:
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.270
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.417
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.280
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.081
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.276
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.451
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.254
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.394
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.419
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.149
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.463
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.676

[NanoDet][01-26 20:17:31]INFO:
| class         | AP50   | mAP   | class          | AP50   | mAP   |
|:--------------|:-------|:------|:---------------|:-------|:------|
| person        | 62.8   | 37.8  | bicycle        | 30.0   | 16.1  |
| car           | 38.5   | 21.3  | motorcycle     | 53.8   | 30.6  |
| airplane      | 76.2   | 56.1  | bus            | 64.0   | 52.1  |
| train         | 80.0   | 60.3  | truck          | 35.1   | 21.9  |
| boat          | 27.5   | 13.1  | traffic light  | 23.1   | 10.4  |
| fire hydrant  | 66.7   | 52.4  | stop sign      | 58.0   | 51.3  |
| parking meter | 49.1   | 31.6  | bench          | 23.3   | 14.1  |
| bird          | 32.4   | 19.4  | cat            | 80.6   | 58.0  |
| dog           | 65.2   | 48.2  | horse          | 60.9   | 39.5  |
| sheep         | 53.9   | 30.4  | cow            | 56.9   | 35.3  |
| elephant      | 75.8   | 51.6  | bear           | 80.0   | 61.8  |
| zebra         | 81.0   | 54.9  | giraffe        | 81.7   | 56.9  |
| backpack      | 9.7    | 5.2   | umbrella       | 41.3   | 24.6  |
| handbag       | 6.3    | 2.9   | tie            | 31.4   | 17.6  |
| suitcase      | 31.0   | 17.5  | frisbee        | 55.6   | 37.5  |
| skis          | 25.5   | 10.9  | snowboard      | 31.0   | 16.8  |
| sports ball   | 30.0   | 19.0  | kite           | 44.7   | 26.0  |
| baseball bat  | 28.7   | 12.9  | baseball glove | 39.4   | 19.4  |
| skateboard    | 51.3   | 28.6  | surfboard      | 40.1   | 21.4  |
| tennis racket | 49.9   | 26.9  | bottle         | 24.5   | 13.2  |
| wine glass    | 22.6   | 12.7  | cup            | 28.6   | 18.4  |
| fork          | 22.3   | 12.6  | knife          | 6.7    | 3.6   |
| spoon         | 6.0    | 2.6   | bowl           | 36.8   | 25.2  |
| banana        | 32.6   | 17.7  | apple          | 15.8   | 10.4  |
| sandwich      | 42.5   | 27.3  | orange         | 31.1   | 22.9  |
| broccoli      | 31.0   | 15.3  | carrot         | 28.1   | 13.6  |
| hot dog       | 36.2   | 23.4  | pizza          | 56.7   | 41.6  |
| donut         | 39.9   | 28.5  | cake           | 35.8   | 22.8  |
| chair         | 22.8   | 12.3  | couch          | 54.1   | 36.8  |
| potted plant  | 24.4   | 12.3  | bed            | 62.0   | 43.7  |
| dining table  | 37.2   | 25.5  | toilet         | 71.8   | 53.4  |
| tv            | 64.9   | 45.0  | laptop         | 59.6   | 44.4  |
| mouse         | 57.5   | 37.7  | remote         | 14.8   | 6.9   |
| keyboard      | 57.8   | 36.9  | cell phone     | 26.5   | 18.5  |
| microwave     | 53.9   | 38.7  | oven           | 42.6   | 26.6  |
| toaster       | 30.5   | 17.6  | sink           | 41.4   | 24.9  |
| refrigerator  | 58.5   | 42.6  | book           | 13.5   | 5.7   |
| clock         | 55.0   | 32.3  | vase           | 28.2   | 17.6  |
| scissors      | 25.5   | 18.5  | teddy bear     | 50.6   | 33.3  |
| hair drier    | 0.2    | 0.0   | toothbrush     | 12.2   | 6.4   |

[codecov]

Codecov Report

Merging #395 (35b72b5) into main (8cb9044) will increase coverage by 0.20%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #395      +/-   ##
==========================================
+ Coverage   74.05%   74.25%   +0.20%     
==========================================
  Files          66       66              
  Lines        4424     4459      +35     
  Branches      752      756       +4     
==========================================
+ Hits         3276     3311      +35     
  Misses        969      969              
  Partials      179      179              

Flag	Coverage Δ
unittests	74.25% <100.00%> (+0.20%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
nanodet/data/dataset/coco.py	72.82% <100.00%> (+0.29%)	⬆️
nanodet/evaluator/coco_detection.py	92.20% <100.00%> (+6.16%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 8cb9044...35b72b5. Read the comment docs.