ousheng

Or the yolov3 model provided by default, which resolution is based on?

Thank you, I get it

@GiBeom-Song Is the problem solved?

hi, when i run the test.py, also have the same problem. i use python3.5 @VideoObjectSearch Traceback (most recent call last): File "test.py", line 32, in from keras_alfnet.model.model_1step import Model_1step File...

@404hasbeenfound 请问，解决了吗，能否提供思路

@YinRui1991 谢谢回复，已尝试，可以。再请教下，作者默认是deepsort对人的跟踪，车的话使用效果怎么样

> > @YinRui1991 谢谢回复，已尝试，可以。再请教下，作者默认是deepsort对人的跟踪，车的话使用效果怎么样 > > 我没有尝试进行车的跟踪，如果你要用deep sort跟踪车你得自己训练个车的mars-small128.pb用来提取车的特征，或者我觉得也可以用检测器的某几层取下特征。deep_sort用了卡尔曼滤波+级联特征匹配，要两者兼备效果才好。 再次感谢答复，下一步可以尝试训练或者尝试其他网络特征

@Akhtar303nu Has it been resolved

Thanks for sharing, it would be better if there is export onnx for independent deployment, not just triton

这个功能可以有