Single Image Metrics - Githubissues

rafaelpadilla / review_object_detection_metrics

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

Other

1.09k stars 215 forks source link

Single Image Metrics #41

Closed joeization closed 3 years ago

joeization commented 3 years ago

Is there any way to produce metrics of each image separately? Or I should split gt/det here? https://github.com/rafaelpadilla/review_object_detection_metrics/blob/e32521be14e9c2372bda204c1e30648188c71b21/src/ui/run_ui.py#L336

rafaelpadilla commented 3 years ago

Hi @joeization,

@joeization ,

You could split gt and dets the way you mentioned, or you could use the function get_pascalvoc_metrics, passing the argument generate_table=True.

Then you will get a pandas object and obtain a similar table like this one, and get the metrics from there.

I hope that helps.

joeization commented 3 years ago

Thanks for your reply