search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.75k stars 7.96k forks source link

Labelled file in absolute coordinates #5697

Open pablus09 opened 4 years ago

pablus09 commented 4 years ago

Hi, I need the absolute coordinates, nor the relative ones. Is there any posibility to obtain it? Thanks.

NHarishGit commented 4 years ago

I have no affiliation with the makers but here you go:

https://github.com/puzzledqs/BBox-Label-Tool https://github.com/tzutalin/labelImg https://github.com/developer0hye/Yolo_Label

Lat one might be normalizing the pixel coordinates but since you have asked this in YOLO forum !

MikhailMurashov commented 4 years ago

+1 Little bit confused. How to convert pseudo-lableing "relative_coordinates":{"center_x":0.420084, "center_y":0.419855, "width":0.048855, "height":0.079983} to bbox = (x, y, w, h) such as in OpenCV? Thanks.

AlexeyAB commented 4 years ago

https://github.com/AlexeyAB/darknet#how-to-use-on-the-command-line

Pseudo-lableing - to process a list of images data/new_train.txt and save results of detection in Yolo training format for each image as label .txt (in this way you can increase the amount of training data) use: darknet.exe detector test cfg/coco.data cfg/yolov4.cfg yolov4.weights -thresh 0.25 -dont_show -save_labels < data/new_train.txt

NHarishGit commented 4 years ago

+1 Little bit confused. How to convert pseudo-lableing "relative_coordinates":{"center_x":0.420084, "center_y":0.419855, "width":0.048855, "height":0.079983} to bbox = (x, y, w, h) such as in OpenCV? Thanks.

= / or = / attention: - are center of rectangle (are not top-left corner)