Open ozanpkr opened 2 years ago
You need to convert boxes in x1, y1, x2, y2 format, then normalize (using image width and height).
xn1 = x1 / image_width
yn1 = y1 / image_height
xn2 = (x1 + width) / image_width
yn2 = (y1 + height) / image_height
then you can apply WBF.
You need to convert boxes in x1, y1, x2, y2 format, then normalize (using image width and height).
xn1 = x1 / image_width yn1 = y1 / image_height xn2 = (x1 + width) / image_width yn2 = (y1 + height) / image_height
then you can apply WBF.
Thanx for quick reply :) I'll let you know about results
I wanna use this repo with mmdetection result.I edited Json and converted to CSV format.However I get 0 for mAP and Recall. I can share my csv and ground_truth.json files via drive link.In addition you can see my detection output for model_1 below;![out_det](https://user-images.githubusercontent.com/59290581/132311130-70f4f647-fbbf-41ea-9be1-b30de802f086.PNG)
You can see json2csv script on below;
I think normalization process is wrong my code or ground_truth.json configuration is false.Could you help me ? You can access all code with this URL:
https://github.com/ozanpkr/Weighted-Boxes-Fusion/tree/master/ozan
Could you normalize this bbox? format=[x1,y1,width,height] !!!(x1,y1) refer to upper left [148,186,72,96] =??