LamHoCN
LamHoCN
by merlin
有意义
无意间查看darknet的时候发现了你的项目,觉得蛮有意义。 因为项目上的需要,用darknet也算比较长时间了,对yolo进行过caffe以及嵌入式单hpp的整体算法移植,对darknet算是烂熟于心了。现在darknet也成了我进行算法验证的直接框架,DeepCompression,mobilenet 等算法也基于darknet进行了验证。并且为darknet的增添了多分支的数据传输结构。 希望可以帮助到你。不过我都是在gpu端进行的改写或者实现。
hey TRI guys , what a fancy work ! Can you show me how do I train zero-depth on my own data?I didn't find some trainning config. Thx a lot...
 hey, how to vis like above in the paper ?
what a great work ! I want to know when to openSource the trainning code, Thx ~
hey brummi ~ I have some question with FisheyeToPinhole. I tried to visualize the fisheye img after this sample function. I used the kitti360 data_fisheye_calibration data and calibration results which...