facebookresearch/segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Jupyter NotebookApache-2.0
Issues
- 1
Checkered Predictions (Checkered Artifacts?)
#778 opened by Vishawjeet-rmsl - 3
- 2
DEMO WARNING: Critical dependency: require function is used in a way in which dependencies cannot be statically extracted
#777 opened by WCH-Jason - 7
What is the shape of the encoder's boxes?
#739 opened by raoxinyu4977 - 7
- 1
Problem with using model checkpoint and PytorchStreamReader failed reading zip archive: failed finding central directory
#776 opened by lindawang0122ds - 0
can use multi-boxes prompt to fine-tune SAM?
#775 opened by wu2233 - 0
SAM 1.0 vs SAM 2.0 , which one should you choose? Detailed Video on youtube.
#774 opened by thedatamask - 2
The everything generation of official Demo
#737 opened by kuazhangxiaoai - 1
Define granularity of segmented areas
#770 opened by abrahamezzeddine - 0
Need help
#772 opened by abhishekbiswas772 - 0
- 1
Application in cell detection
#769 opened by GiangTranHU - 0
- 0
- 0
How to make sam( vit_l onnx ) faster.
#766 opened by Siwakonrome - 2
Question of the final masks
#765 opened by zkjisj - 0
export encoder from onnx to tensorrt
#764 opened by junwei0812 - 2
How can I use python to achieve the effect demonstrated by the demo, so that the mask of the corresponding area appears when hovering?
#727 opened by Bruce337f - 2
How to segment the Gundam in image? Any suggestion?
#761 opened by garrisonz - 1
SAM for dynamic aspect ration images
#760 opened by mariiak2021 - 2
- 0
how can i generate the overlay picture ?
#759 opened by xiong76 - 2
- 0
- 4
Incorret result scaling
#753 opened by neko-para - 2
Error in apply_image function?
#754 opened by melisandeteng - 0
Fine-tuning reproducibility with GPU
#752 opened by alanwilter - 0
the results in gpu and cpu are different.
#751 opened by zhangvia - 0
could you please explain what are the role of crop_overlap_ratio and crop_n_points_downscale_factor parameters?
#750 opened by jetsonwork - 2
Trying to use SAM to segment engineering rock samples, but I need to solve two issues
#749 opened by citystrawman - 1
How to generate polygons from the mask ?
#742 opened by mohamedusmb - 2
YOLO&SAM onnx exporter
#748 opened by yanzongs - 0
- 0
pip package request
#746 opened by myron - 0
Grid with a different number of points per side
#745 opened by hellcastter - 3
Get Image Embedding Vector and Store it in DATABASE
#740 opened by cepa995 - 0
- 0
Finetune SAM for instance segmentation to output segmenatation masks along with label names
#741 opened by Abonia1 - 0
- 2
Why is the output of the Image Encoder here a tensor with the shape of (64, 64, 256) instead of a one-dimensional vector?
#736 opened by FangehaPlus - 0
Excuse me, can this project separate hair strands? I see that the segmented hair mask has a background
#735 opened by hjj-lmx - 0
Is there a way the save the mask objects by SAM?
#734 opened by XiangyuLijoey - 0
Will this package be maintained?
#733 opened by sdtaylor - 3
"Empty" box input
#731 opened by 25benjaminli - 0
missing "predict.py & cog.yaml"
#732 opened by abrar-tericsoft - 0
How is ViTDet backbone pretrained with MAE?
#729 opened by prakashjayy - 3
Sam decoder model is returning the error : Cannot read property 'buffer' of undefined, when i try to load the sam encoder image embeddings with .txt file extension. Using ONNX react-native runtime.
#726 opened by Saikumar-gadde517 - 1
- 3
https://segment-anything.com/demo is working fine. But my local scripts/amg.py is not working as well as https://segment-anything.com/demo
#725 opened by tugsjargal1