facebookresearch/sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Jupyter NotebookApache-2.0
Issues
- 1
The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 1
#572 opened by hjj-lmx - 0
Missing method `clear_non_cond_mem_around_input`
#571 opened by tonydavis629 - 0
hydra.errors.InstantiationException: Error in call to target 'training.trainer.Trainer':
#568 opened by zhoustan - 0
- 1
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
#540 opened by SDragon1205 - 0
Demo only shows the first 9.23 seconds of the video
#569 opened by ebozcal - 1
Pt2onnx encountered omegaconf error
#529 opened by oowwkk - 0
automatic mask generation
#552 opened by chevalierNoir - 2
- 1
Can I use SAM2 for video segmentation on a CPU ?
#564 opened by Juni188 - 0
- 3
Muticamera person Reidentification
#563 opened by nishant0708 - 2
Support ROCm
#562 opened by githust66 - 2
- 3
Refining masks after propagation?
#546 opened by Zarxrax - 0
Documentation for Flask & Sam2 integration
#560 opened by upasana-mittal - 0
Real time background removal for human live streaming?
#559 opened by aihkla - 0
是否可以自动识别到视频中的所有文字,不需要框选
#556 opened by hjj-lmx - 0
Sth wrong with SAM2 demo
#554 opened by 21882etc - 0
关于模型训练的几个问题?
#553 opened by retioa11 - 1
Can I install and run SAM2 with AMD RADEON?
#551 opened by sabry9999 - 1
Finetune a differnt variant of SAM2
#550 opened by aditya-nisal - 8
Large video and loading in batches
#545 opened by horsto - 0
- 0
- 4
- 3
Loading models on Cloud services not working when using build_sam2 but works on Windows I am giving accurate paths
#544 opened by FurkanGozukara - 1
- 2
- 0
Regarding Image format Sam2 Support
#542 opened by lukiod - 0
YAML Script for Fine-Tuning with SAM2.1 Large
#541 opened by Inbalc2 - 0
- 0
How to implement an "undo"?
#538 opened by Zarxrax - 3
I gave same prompt input but makes different result in video and single image prediction
#533 opened by tissuemother - 0
default num_maskmem =7 can we change thing number
#536 opened by manoj-samal - 0
Mask "Bleeding out"
#535 opened by DonggeonKim1012 - 0
- 0
Inquiry of base_lr and vision_lr
#532 opened by gogochen07 - 1
Different output depending on if points are added incrementally or all at once
#526 opened by Zarxrax - 0
MissingConfigException Issue
#531 opened by AChowdhury1211 - 0
Use the training methods provided by sam2 to train the object detection dataset
#530 opened by havinggood - 2
- 0
复现MOSE数据集上的训练过程
#525 opened by havinggood - 0
About _apply_non_overlapping_constraints
#527 opened by King-king424 - 1
When do I need to reset_state()?
#523 opened by Zarxrax - 0
Problem selecting pixels in the first frame
#522 opened by Liuhsinlun - 0
- 1
- 0
Track multiple targets
#521 opened by elmayana - 0