meta_trackers icon indicating copy to clipboard operation
meta_trackers copied to clipboard

The doubt about random results

Open jimmy-dq opened this issue 6 years ago • 1 comments

Hi, @silverbottlep , thaks for your excellent work. I just run your code (meta_sdnet/run_tracker.py) and find that you fix the seed in the experiment, like np.random.seed(1), torch.manual_seed(2) and torch.cuda.manual_seed(3). But i still find that the result is random, could you explain this ?

jimmy-dq avatar Mar 09 '18 06:03 jimmy-dq

Yes, I also met the same problem. Is there any solutions for that?

best

zhanglichao avatar May 09 '19 08:05 zhanglichao