关于input image是RGB or BGR

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

MIT License

1.18k stars 313 forks source link

关于input image是RGB or BGR #49

Closed lq0104 closed 3 years ago

lq0104 commented 3 years ago

您好，还想请教一个问题，AlexeyAB darknet训练基于的格式是RGB格式，opencv默认读出来的格式是BGR格式，请问您的代码中对通道做了转换吗，还有图像归一化使用的mean和std都是多少呀

enazoe commented 3 years ago

@lq0104 做了转换，已经转成rgb了，归一化部分https://github.com/enazoe/yolo-tensorrt/blob/master/modules/yolo.cpp#L201

lq0104 commented 3 years ago

好的，多谢解答