deep_sort_yolov3
deep_sort_yolov3 copied to clipboard
Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
Hi, I'm running this code on my CPU machine. How do I make it run on the GPU ? Maybe I'm missing something but couldn't find a documentation on how...
@Qidian213 您好!感谢您做出的贡献! 我在在运行demo.py时出现了问题,报错  前面生成.h5文件及mars-small128.pb都成功了,但是不知道为什么最后运行demo.py失败了,请问有人能够解答一下吗?
Thank you for the great implementation of the algorithm. I am curious about this section ``` if predicted_class != 'person' : continue ``` How do think, if a network is...
hello,where is your tracking matrix,i want draw route each id,so i need to find track matrix
您好,请问这个许可以改成 MIT许可 么?
ID不稳定该怎么解决呢?我是想把同一个ID 的人放到同一个文件夹下面,但是发现ID很不稳定,请问我应该怎么解决呢?
关于人员重识别
@Qidian213 你好, nwojke的deep_sort中使用cosine-softmax分类器,你提到的Triplet Loss with hard negative mining 是nwojke在他的论文中提到的 triplet loss.方式吗
非常感谢楼主的分享,运行demo.py时,fps只有0.5左右,请问如何修改能达到实时的效果?输出的视频能够流畅一些呢?
Hello,I would like to know that if there is anyone working actively on the improvement of this tracker?