Coco Api Evaluation For Subset Of Classes

I'm using the python coco api to run evaluation for object detection. I have two files, a ground truth json, and a results json. The coco notebook demo only shows running eval for

Solution 1:

I refer to this page (http://www.programmersought.com/article/3065285708/)

cocoEval = COCOeval(cocoGt,cocoDt,annType)
coco_eval.params.catIds = [1] #person id : 1
cocoEval.params.imgIds = imgIds   
cocoEval.evaluate()  
cocoEval.accumulate()  
cocoEval.summarize() 

Additionaly, I modified cocoapi/PythonAPI/pycocotools/cocoeval.py to calculate AP for each category. https://github.com/kimyoon-young/centerNet-deep-sort/blob/b694fc52f880dfbba481d43a7d5284a29f386ca7/tools/cocoeval.py#L458-L464

The result is like below.

category : 0 : 0.410733757610904 #person AP category : 1 : 0.20226150054237374 #bird AP .... category : 79 : 0.04993736566987926 (all categories) mAP : 0.27999824034118914 # my results Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.280 #original

Solution 2:

In lines 458-464 of https://github.com/kimyoon-young/centerNet-deep-sort/blob/master/tools/cocoeval.py, to support a flexible number of categories, you can replace line 458 (num_classes = 80) with

num_classes = len(p.catIds)