HelloRicky123

Display wrong at the last few lines using tmux on a remote server.

1

**Describe the problem**: Thanks for your work. I use tabby shell 1.0.170 on Windows 10 17763.2928. I log in to the remote Linux server. If I use tmux, the last...

what's your accuracy

7

So, can you provide your accuracy on OTB or VOT? I reimplement the paper and use the same network with you, without imagenet pretrain or Youtube-BB dataset and get at...

Advice to speed up

1

I think you can put as many as possible part in __getitem__ method of dataset.py to __init__.py. And use torch.grid_sample may speed up the padding and crop process.

Tensorboard 2.10.0 does not combine mutliple event files automatically.

1

## Environment information (required) ### Diagnostics Diagnostics output `````` --- check: autoidentify INFO: diagnose_tensorboard.py version df7af2c6fc0e4c4a5b47aeae078bc7ad95777ffa --- check: general INFO: sys.version_info: sys.version_info(major=3, minor=8, micro=8, releaselevel='final', serial=0) INFO: os.name: posix INFO:...

The edit_cli runs well but edit_app returns nothing.

2

Hi, thanks for the excellent work. I have configured the repository according to the instructions provided in the README document. The edit_cli runs well and produces the edited image as...

The original paper said that the training including 200K iters costs 14 hours on a single V100. But the default code set the training iteration as 100K. In my practical...

I met a strange bug in training, and the learned parameters of smpl cause it. After about 100 epochs, the learned vertices of a frame may become non and the...

Inquiry of code publication schedule

2

Hi, TELA is an excellent piece of work. I would like to conduct some experiments based on it. Could you please let me know when the code will be made...