search

dbolya / tide

A General Toolbox for Identifying Object Detection Errors
https://dbolya.github.io/tide
MIT License
702 stars 115 forks source link

Can I use TIDE on my own dataset - given coco-formatted Ground-Truth and predicted Bounding Boxes? #51

Open codingbutstillalive opened 1 year ago

codingbutstillalive commented 1 year ago

I mean, I intuitively thought so. But then I read "The currently supported datasets are COCO, LVIS, Pascal, and Cityscapes. More details and documentation on how to write your own database drivers coming soon!". So I am wondering. I mean.. this shouldn't really be an issue.

ZHAOBenyun commented 4 months ago

hi, have you solved this problem?

Michael-24 commented 3 months ago

Traceback (most recent call last): File "/home/gonglianghao/object_detection/ultralytics4.12/get_COCO_metrics.py", line 50, in gt = datasets.COCO(annFile) File "/home/gonglianghao/miniconda3/envs/yolov8_new/lib/python3.9/site-packages/tidecv/datasets.py", line 102, in COCO mask = f.toRLE(ann['segmentation'], image_lookup[image]['width'], image_lookup[image]['height']) File "/home/gonglianghao/miniconda3/envs/yolov8_new/lib/python3.9/site-packages/tidecv/functions.py", line 90, in toRLE rles = maskUtils.frPyObjects(mask, h, w) File "pycocotools/_mask.pyx", line 293, in pycocotools._mask.frPyObjects IndexError: list index out of range how can i fix this?