The problem of classifier in ATOM

[xyl-507]

Hello, the author. Thanks for the outstanding contribution！ When I run the ATOM, there was a problem that this part of code must be commented out：

Train filter

    if hard_negative:
        self.filter_optimizer.run(self.params.hard_negative_CG_iter)
    elif (self.frame_num-1) % self.params.train_skipping == 0:
        self.filter_optimizer.run(self.params.CG_iter)

If it is not commented out, the tracker will be very slow, and the GPU utilization will be full, resulting in the inability to completely test a dataset. I don't know the reason, would you please give me some suggestions? Thanks in advance!

[martin-danelljan]

Hi. Seems very strange. What GPU do you have?

[xyl-507]

@martin-danelljan 2080Ti