xuqingyu

Evaluate problem

2

Hello, recently, i am working on the rgbt challenge, and when i try to run my tracker using the vot-toolkit-python, i run into some problems, as follows: Checking for new...

It's our great pleasure to see the update of this repository, for the new man to be quickly familiar with the hot point of MOT domain.

The backpropagation part is needed?

1

I think with the definition of the network and loss function, the backpropagation should be auto computed, why should we explicitly definite it in the code?

The environment is: torch1.11+cu11.3+python3.8+ubuntu22.04 And the project is seccessfully compiled. When run the testcuda.py ,i run into the following questions: error in modulated_deformable_im2col_cuda: no kernel image is available for execution...

The loss of the tracking decoder

2

Hello, thanks for your excellent work, and i would like to know the reason why the loss of tracking decoder is hard to decrease when applied on my custom small...