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
1.08k stars 215 forks source link

no file was found in the selected detection format in the annotations directory - for detections only #85

Closed apecundo closed 2 years ago

apecundo commented 3 years ago

Hi Rafael,

Good day! I have tried testing this on my dataset, and ground truth detection works fine.

However, for the detection files, following the format prescribed, I am getting an error saying that "no file was found in the selected detection format..".

I have tried double checking the other previous issues related to this as well but I am still stuck getting this error. I have tried double checking the format and it seems to be aligned with the prescription.

May I request for your help understanding if I have missed anything else required for the file preparation?

For your reference, I am using the detection format of

detections_allan.zip

Thank you so much for this!

Regards Allan

AMF2601 commented 3 years ago

Same error when testing for YOLOv5 format

AMF2601 commented 3 years ago

Same error when testing for YOLOv5 format

Solved it. It was due to the complex file name of the label and image file. Rename the images and labels to a simple format. Ex: 1.jpg and 1.txt. The confidence score can be added to the label file by running detect.py --save-txt --save-conf.

zxq309 commented 2 years ago

Same errors occurred. please help me?? metrics_visualization.zip

github-actions[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.