Per class recall
aorad opened this issue · comments
Do you plan on supporting per class metrics?
Support already exists, but is buried a little deeper in the code.
However, recall will not be supported. Just use COCOEval for that.
run = tide.evaluate(gt, results)
for class_id, ap_data in run.ap_data.objs.items():
print('{:10s}: {:.2f}'.format(str(class_id), ap_data.get_ap()))
This will print out the AP for each class ID individually for the given run.
I am getting different results using this vs the pyCoco tools. Is there a reason for that?
The code I showed gives you the per-class mAP @ 50. the COCO evaluation toolkit probably gives you @ 50:95.
No not using the code, using the entire project.
the mAP values for the evaluation are different
Can you create a new issue for this with what TIDE outputs vs. what pycocotools outputs?