Confusion about the output of scale_boxes in Week3

[arosacastillo]

Hi LuBinLiu,

Great to see that you try to understand the outputs.
Yes, I recommend that you have a look at the scale_boxes function, code is available

Problems with YAD2K

Hello, How can I check for the source code of some fuctions, that were implemented already? Fox example, scale_boxes(boxes, image_shape) in the Course 4 the “Car Detection with YOLO” task. I went into GitHub - allanzelener/YAD2K: YAD2K: Yet Another Darknet 2 Keras, but could not find some function there, such as scale_boxes, read_classes, read_anchors [scale_boxes] Addionally, I would like to use some files in my own project, such as “model_data/coco_classes.txt” or “model_data/yolo_anchors.…

As said in the thread it is transforming the yolo coordinates to some generic box coordinates, that is why the big numbers.

Happy learning,

Rosa