rmx564354093

 

我是用你的代码跑的 把亚像素关掉就不会越界 开启亚像素就会有数组越界的地方

用最新的代码 开启亚像素 没有崩溃现象了 但是亚像素是否开启 好像坐标没啥变化

why not write a barcode function

I really need the libtorch training version of yolo5 or yoloX, but it’s a bit difficult for me to implement it myself Looking forward to your realization

I changed train.prototxt test.prototxt deploy.prototxt resize_param or dimensions from 300 to 150 and then train again but the result of detect is very bad. Do you still need to modify...