Skip to content

Issues: IDEA-Research/Grounded-SAM-2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

27 Open 26 Closed
27 Open 26 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

error in ms_deformable_im2col_cuda: no kernel image is available for execution on the device
#71 opened Nov 25, 2024 by Ran0618
Minimum image size?
#70 opened Nov 16, 2024 by neilkale
Unexpected label during prediction
#66 opened Oct 31, 2024 by yuerout
4
Train GroundedSAM2 with custom dataset
#63 opened Oct 30, 2024 by Aseni95
1
support a sentence as text_prompt for Ground and Tracking?
#62 opened Oct 29, 2024 by shixishi
1
When new category of objects occur in the later frame, which are not prompted in the first frame, are there some good methods to tracking the new objects? discussion
#58 opened Oct 8, 2024 by RongkunYang
2
Object class_name BUG?
#54 opened Sep 25, 2024 by Li-jinnan
RuntimeError("No points are provided; please add points first") during reverse tracking
#53 opened Sep 25, 2024 by SJP2022
3
Output class names return ungiven classes
#50 opened Sep 20, 2024 by CYBruce
1
When using grounded_sam2_florence2_image_demo.py, error
#48 opened Sep 12, 2024 by ChinChyi
1
If our video does not initially contain the object we want to detect, how should we modify the code? discussion
#45 opened Sep 5, 2024 by Zhujx-zjjx
4
Tracking with continuous id crashes when does not find input boxes
#43 opened Sep 3, 2024 by photosartd
1
ms_deform_attn_forward_cuda" not implemented for 'BFloat16 bug Something isn't working documentation Improvements or additions to documentation
#38 opened Aug 29, 2024 by ChinChyi
7
Making SAM 2 run 2x faster enhancement New feature or request
#37 opened Aug 28, 2024 by mvoodarla
3
ImportError: flash_attn not found when running grounded_sam2_florence2_image_demo.py
#35 opened Aug 25, 2024 by XiaowenZhang-kuku
6
Florence-2 vs Grounding DINO + SAM2 discussion
#34 opened Aug 24, 2024 by radames
1
While running grounded_sam2_local_demo.py facing following warning
#30 opened Aug 23, 2024 by Jaykumaran
2
Support image prompt discussion
#29 opened Aug 22, 2024 by wentao-uw
2
prompt type for video issue
#28 opened Aug 21, 2024 by ZhangT-tech
3
Assertion Error
#26 opened Aug 20, 2024 by Masrur02
5
Predict from a video file
#25 opened Aug 20, 2024 by Masrur02
3
GroundingDINO Import Error documentation Improvements or additions to documentation
#24 opened Aug 19, 2024 by cremebrule
3
Is there a parameter in the code that can control the tracking accuracy of the video predictor and reduce the false positives (FP)?
#22 opened Aug 19, 2024 by melodyhappy
1
How about 3D version?
#20 opened Aug 19, 2024 by StarsTesla
3
How to track new objects? discussion enhancement New feature or request
#19 opened Aug 18, 2024 by melodyhappy
4
ProTip! Find all open issues with in progress development work with linked:pr.