Shape error when trying to use default mask/setting refine_enable to False
- Dominant language
- Python
- Stars
- 3.6k
- Forks
- 804
- PR merge metrics
- No merged PRs in 30d
Description
First of all, thanks for such a great project.
When trying to run demo.py and setting refine_enable to False, thus using the default mask, I`ve encountered an issue:
```
Traceback (most recent call last):
File "../../tools/demo.py", line 55, in
state = siamese_track(state, im, mask_enable=True, refine_enable=False, device=device) # track
File "/home/zeleniyslonik/PycharmProjects/SiamMask/tools/test.py", line 261, in siamese_track
mask = mask[0, :, delta_y, delta_x].sigmoid(). \
RuntimeError: shape '[127, 127]' is invalid for input of size 3969
```
I am running it on a default tennis demo. Can you give me any advice on how to properly implement the usage of the default mask? I need it to compare the results between the refined mask and itself. Thanks in advance.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.