search

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

Output summary table? #37

Closed crash1001 closed 3 years ago

crash1001 commented 3 years ago

Is there any way to print tables with columns for image_frame, TP, FP for all classes in the ground truth like a summary report? I need to make a comparison based on the number of TP and FP detections for all the classes and need to know in which image_frame the FP occurred.

rafaelpadilla commented 3 years ago

Hi @crash1001,

It is possible to generate a table like this one. Each line represents a detected bounding box, confidence, IOU, and if it is a FP or TP (IOU>threshold). You could adapt this table adding a column with the image name and group the detections considering each image.

By that, you have to pass the argument generate_table=True to the function get_pascalvoc_metrics. See it here for more details.

I hope it helps.

rafaelpadilla commented 3 years ago

As no activity has been performed in this issue, I decided to close it.

If anyone decides to add any comment or have doubts on this topic, feel free to reopen the issue.