passion3394
passion3394
@cardwing yes, I have seen the #7 issue, I will try it. Have you tried to inference more than 4 lanes? and what's the precision ?
@cardwing ok, thanks for your work.
its may be about the system environment, I have successfully installed this project on centos7 system with GPU 2080ti. Go to https://github.com/passion3394/darknet2caffe_yolov3
遇到同样的问题，作者能出来解释一下嘛，多谢！
yes, I followed the note 4 to split the original yolov3-tiny prototxt to two prototxt, the result is very bad.
the original Darknet model works normally, but the converted yolov3-tiny-1.prototxt and yolov3-tiny-2.prototxt can only detect a point, which is the center of the object.
@dd110hh110 please refer the link on the readme of this repo, the author has published the two spited prototxt in the Baidu net disk. https://pan.baidu.com/s/1yiCrnmsOm0hbweJBiiUScQ
@dd110hh110 我觉得作者的这种实现方式可能有点问题，期待作者能改进
@JiaRenChang hi, I use the Apollo depth dataset to train the model, the learning rate is calculated by the following formular 'lr = 0.01 * 0.1 ** (epoch // 30)'....
@JiaRenChang Yes, the depth of movable objects have been eliminated. Dear author, I have three questions about the PSMNet, hope to get the answers from you: (1)If we use the...