lwzhaojun

Results 4 issues of lwzhaojun

The training objective in the original paper is theta. Should the loss value be theta? Why is loss in your program a cross entropy loss?

Hello, thank you very much for your code. I want to start from scratch on the new data set without calling the pre-training weights. May I ask what operation is...

I see that you have adapted it from deepstream-test5-app to implement the function of people flow statistics. Can you realize the statistics of traffic flow? Where to modify it?

Where is the program of draw line and count people crossing the line? I did not find it.