meta_trackers

meta_trackers copied to clipboard

The doubt about random results

1

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...

jimmy-dq

The tracking code is missing images.txt and otb_100, and the VID dataset can't be done now.

guwenning

At line 52 in file 'meta_crest/model.py', there is a usage of variable 'weights', but I do not find where is the definition of 'weights'.

gzpan

#### Hello, I can't understand why `create_graph` arguments in these places([here](https://github.com/silverbottlep/meta_trackers/blob/e48698bb419e25357955ffc2f67bca5c64e3f8d1/meta_sdnet/meta_pretrain/train_meta_init.py#L57), [here](https://github.com/silverbottlep/meta_trackers/blob/e48698bb419e25357955ffc2f67bca5c64e3f8d1/meta_sdnet/meta_pretrain/train_meta_init.py#L67)) are `True`, because the result, grads, aren't used to calculate higher order derivative products. Am I wrong ?...

SMZCC

#### Hello, thanks for your contribution :+1: - Just as the title mentioned, would you please share the results of the 30-15-pyMDNet ? ##### Thanks in advance! ##### Best regards

SMZCC