search

WisconsinAIVision / MixNMatch

Pytorch implementation of MixNMatch
975 stars 189 forks source link

Bounding Box #19

Closed avilatner closed 3 years ago

avilatner commented 3 years ago

What implementation did you use to get the bounding box in that format? I can see that (x, y, w, h) is the pixel distance from the top and left, I just don't know of a library that uses that format.

avilatner commented 3 years ago

Is it YOLO format and https://github.com/tzutalin/labelImg ?

Yuheng-Li commented 3 years ago

Sorry, I do not fully understand your question.

But if you are asking where to get boxes, typically, they are provided (such as CUB http://www.vision.caltech.edu/visipedia/CUB-200-2011.html). If you do not have boxes for your own dataset, we suggest that you fire a pretrained detector.

If you are asking how to get xywh format, then you can write your script to convert from whatever you have now to xywh format.

avilatner commented 3 years ago

Thanks, Yuheng-Li. You answered my question. I wasn't sure if it was (x,y,w,h) or (x1,y1,x2,y2) or another format and wanted to validate before I start training.