facebookresearch/segment-anything issues and pull requests

#796 - Add Replicate demo link

Pull Request - State: open - Opened by deepfates 8 days ago - 2 comments
Labels: CLA Signed

#795 - Masks not aligned with image

Issue - State: open - Opened by AaronLopes 9 days ago

#794 - Do we need to finetune the models for bounding box based prompt and points-based prompt separately?

Issue - State: open - Opened by ywangwxd 10 days ago

#793 - Whether it is possible to do semantic segmentation without prompts or dots

Issue - State: open - Opened by lucky-asia 11 days ago - 1 comment

#792 - How to use masks prompt

Issue - State: open - Opened by wu2233 17 days ago

#792 - How to use masks prompt

Issue - State: open - Opened by wu2233 17 days ago

#791 - SamAutomaticMaskGenerator after more than 2 in parallel process becomes very slow

Issue - State: open - Opened by 0930mcx 18 days ago

#791 - SamAutomaticMaskGenerator after more than 2 in parallel process becomes very slow

Issue - State: open - Opened by 0930mcx 18 days ago

#790 - Bounding Box on each cutout

Issue - State: closed - Opened by MalikHaroonKhokhar 19 days ago - 1 comment

#789 - segment anything model running out of memory

Issue - State: closed - Opened by MalikHaroonKhokhar 28 days ago - 3 comments

#788 - panoptic segmentation

Issue - State: open - Opened by ZixinxinWang about 1 month ago

#783 - Fix critical dependency warning in webpack config

Pull Request - State: open - Opened by HendricksJudy about 1 month ago - 1 comment
Labels: CLA Signed

#777 - DEMO WARNING: Critical dependency: require function is used in a way in which dependencies cannot be statically extracted

Issue - State: open - Opened by WCH-Jason about 2 months ago - 5 comments

#776 - Problem with using model checkpoint and PytorchStreamReader failed reading zip archive: failed finding central directory

Issue - State: open - Opened by lindawang0122ds 2 months ago - 1 comment

#775 - can use multi-boxes prompt to fine-tune SAM?

Issue - State: open - Opened by wu2233 2 months ago

#774 - SAM 1.0 vs SAM 2.0 , which one should you choose? Detailed Video on youtube.

Issue - State: open - Opened by thedatamask 2 months ago

#773 - Multi-click

Pull Request - State: closed - Opened by jingwenhz 3 months ago - 1 comment

#772 - Need help

Issue - State: open - Opened by abhishekbiswas772 3 months ago

#771 - crop_n_layers but do not segment anything other than the last layer

Issue - State: open - Opened by summersonnn 5 months ago

#770 - Define granularity of segmented areas

Issue - State: open - Opened by abrahamezzeddine 5 months ago - 1 comment

#769 - Application in cell detection

Issue - State: open - Opened by GiangTranHU 5 months ago - 1 comment

#768 - how to inference with onnx but no box prompt ,and points prompt?

Issue - State: open - Opened by cqray1990 5 months ago

#767 - pic should be Tensor or ndarray. Got <class 'numpy.ndarray'>

Issue - State: open - Opened by chouliuzuo 5 months ago

#766 - How to make sam( vit_l onnx ) faster.

Issue - State: open - Opened by Siwakonrome 5 months ago

#765 - Question of the final masks

Issue - State: closed - Opened by zkjisj 5 months ago - 2 comments

#764 - export encoder from onnx to tensorrt

Issue - State: open - Opened by junwei0812 5 months ago

#763 - feature/vue support vue3+vite

Pull Request - State: open - Opened by captainIT 5 months ago - 2 comments
Labels: CLA Signed

#762 - Performance Discrepancy Between SAM Model Demo and GitHub Code

Issue - State: open - Opened by i-am-invincible 6 months ago - 6 comments

#761 - How to segment the Gundam in image? Any suggestion?

Issue - State: open - Opened by garrisonz 6 months ago - 2 comments

#760 - SAM for dynamic aspect ration images

Issue - State: open - Opened by mariiak2021 6 months ago - 1 comment

#759 - how can i generate the overlay picture ？

Issue - State: open - Opened by xiong76 6 months ago

#758 - fix: typo in dataset section

Pull Request - State: open - Opened by CharlesCNorton 6 months ago
Labels: CLA Signed

#757 - "show_box()" needs to be changed in "predictor_example.ipynb"

Issue - State: open - Opened by TahaTabatabaei 6 months ago

#756 - vit_b and vit_h models have same size when quantized exported to onnx

Issue - State: closed - Opened by kevinshen1101 6 months ago - 2 comments

#755 - Kernel crashes and Segmentation fault (core dumped)

Issue - State: open - Opened by dadaaichifan 6 months ago - 2 comments

#754 - Error in apply_image function?

Issue - State: closed - Opened by melisandeteng 6 months ago - 2 comments

#753 - Incorret result scaling

Issue - State: open - Opened by neko-para 6 months ago - 4 comments

#752 - Fine-tuning reproducibility with GPU

Issue - State: open - Opened by alanwilter 6 months ago

#751 - the results in gpu and cpu are different.

Issue - State: open - Opened by zhangvia 6 months ago

#750 - could you please explain what are the role of crop_overlap_ratio and crop_n_points_downscale_factor parameters?

Issue - State: open - Opened by jetsonwork 6 months ago

#749 - Trying to use SAM to segment engineering rock samples, but I need to solve two issues

Issue - State: open - Opened by citystrawman 7 months ago - 2 comments

#748 - YOLO&SAM onnx exporter

Issue - State: open - Opened by yanzongs 7 months ago - 2 comments

#747 - Unable to export decoder in onnx format for GPU context

Issue - State: open - Opened by Greg7000 7 months ago

#746 - pip package request

Issue - State: open - Opened by myron 7 months ago

#746 - pip package request

Issue - State: open - Opened by myron 7 months ago

#745 - Grid with a different number of points per side

Issue - State: open - Opened by hellcastter 7 months ago

#744 - Why SAM not able draw polygon in less thickness line area

Issue - State: open - Opened by sravanth1122 7 months ago

#743 - Running SAM in a loop and eventually running out of GPU memory

Issue - State: closed - Opened by bthetford 7 months ago - 2 comments

#742 - How to generate polygons from the mask ?

Issue - State: closed - Opened by mohamedusmb 7 months ago - 1 comment

#741 - Finetune SAM for instance segmentation to output segmenatation masks along with label names

Issue - State: open - Opened by Abonia1 7 months ago

#740 - Get Image Embedding Vector and Store it in DATABASE

Issue - State: open - Opened by cepa995 7 months ago - 3 comments

#739 - What is the shape of the encoder's boxes?

Issue - State: open - Opened by raoxinyu4977 7 months ago - 2 comments

#738 - Is there a way to calculate the f1 score of the masks in amg.py?

Issue - State: open - Opened by XiangyuLijoey 7 months ago

#737 - The everything generation of official Demo

Issue - State: open - Opened by kuazhangxiaoai 7 months ago - 2 comments

#736 - Why is the output of the Image Encoder here a tensor with the shape of (64, 64, 256) instead of a one-dimensional vector?

Issue - State: open - Opened by FangehaPlus 7 months ago - 2 comments

#735 - Excuse me, can this project separate hair strands? I see that the segmented hair mask has a background

Issue - State: open - Opened by hjj-lmx 7 months ago

#734 - Is there a way the save the mask objects by SAM?

Issue - State: closed - Opened by XiangyuLijoey 7 months ago

#733 - Will this package be maintained?

Issue - State: open - Opened by sdtaylor 7 months ago

#732 - missing "predict.py & cog.yaml"

Issue - State: open - Opened by abrar-tericsoft 8 months ago

#731 - "Empty" box input

Issue - State: open - Opened by 25benjaminli 8 months ago - 3 comments

#730 - Torchscript port

Pull Request - State: closed - Opened by rafaelperez 8 months ago - 1 comment

#729 - How is ViTDet backbone pretrained with MAE?

Issue - State: open - Opened by prakashjayy 8 months ago

#728 - Documentation and Tutorial Link Request for Key Code Section

Issue - State: open - Opened by Emilio942 8 months ago - 1 comment

#727 - How can I use python to achieve the effect demonstrated by the demo, so that the mask of the corresponding area appears when hovering?

Issue - State: closed - Opened by Bruce337f 8 months ago - 2 comments

#726 - 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.

Issue - State: open - Opened by Saikumar-gadde517 8 months ago - 3 comments

#725 - 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

Issue - State: open - Opened by tugsjargal1 8 months ago - 3 comments

#724 - [+] add save and load embedding methods in SamPredictor class

Pull Request - State: open - Opened by Kirscher 8 months ago
Labels: CLA Signed

#723 - Multiple coords + Multiple boxes + Multiple labels solution - Need suggest

Issue - State: open - Opened by pnthai88 8 months ago - 4 comments

#722 - How to use it with text prompt

Issue - State: open - Opened by xiyufeng2 8 months ago - 3 comments

#721 - Use a class attribute for type checking

Pull Request - State: open - Opened by ibarraz5 8 months ago
Labels: CLA Signed

#720 - auto generating masks for multiple images and saving them?

Issue - State: closed - Opened by martintmv-git 8 months ago - 1 comment

#719 - Got invalid dimensions for input: mask_input for the following indices

Issue - State: open - Opened by yang-junhua 8 months ago

#718 - Remove torch

Pull Request - State: closed - Opened by ugolotti 8 months ago - 1 comment

#717 - How to get the class label information corresponding to the segmentation mask area?

Issue - State: closed - Opened by hh-xiaohu 8 months ago - 2 comments

#716 - Discrepancy results between online demo and SamAutomaticMaskGenerator

Issue - State: open - Opened by michelbotros 8 months ago - 7 comments

#715 - What is the best way to get only the objects I want?

Issue - State: open - Opened by hanjoonwon 8 months ago - 1 comment

#714 - ONNX model produces worse result than Pytorch counterpart

Issue - State: open - Opened by james-imi 8 months ago - 1 comment

#714 - ONNX model produces worse result than Pytorch counterpart

Issue - State: open - Opened by james-imi 8 months ago

#713 - return low_res logits on SamAutomaticMaskGenerator.generate()

Pull Request - State: open - Opened by jhvital 8 months ago - 2 comments
Labels: CLA Signed

#713 - return low_res logits on SamAutomaticMaskGenerator.generate()

Pull Request - State: open - Opened by jhvital 8 months ago - 2 comments
Labels: CLA Signed

#712 - Add flexibility to SamAutomaticMaskGenerator

Pull Request - State: closed - Opened by jvital-stonify 8 months ago - 1 comment

#711 - Add directory of web screenshots

Pull Request - State: closed - Opened by RDLigeralde 9 months ago - 1 comment

#711 - Add directory of web screenshots

Pull Request - State: closed - Opened by RDLigeralde 9 months ago - 1 comment

#710 - The selection area has obvious jagged problems

Issue - State: open - Opened by bigbear0609 9 months ago - 2 comments

#709 - How to extract each segment feature

Issue - State: open - Opened by Alokksinha00 9 months ago

#709 - How to extract each segment feature

Issue - State: open - Opened by Alokksinha00 9 months ago

#708 - RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) using Crop N layers > 1

Issue - State: open - Opened by bthetford 9 months ago

#708 - RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) using Crop N layers > 1

Issue - State: closed - Opened by bthetford 9 months ago - 1 comment

#707 - Output of labels/pseudo label

Issue - State: open - Opened by bullshit123123 9 months ago

#706 - Prompt detection

Issue - State: open - Opened by tnotariano 9 months ago

#705 - ERR: [wasm] RuntimeError: Aborted in web worker

Issue - State: closed - Opened by boomsi 9 months ago

#704 - Problems with the use of the official website sam(cut out function)

Issue - State: open - Opened by xuyu666 9 months ago - 1 comment

#703 - dimension

Issue - State: open - Opened by HURUDAN 9 months ago

#702 - Grayscale image segmantic segmentation

Issue - State: open - Opened by luckysyj 9 months ago - 1 comment

#701 - Is it possible to limit the number of splits?

Issue - State: open - Opened by hj6hki123 9 months ago

#700 - How can I combine SamAutomaticMaskGenerator with SamPredictor to process a picture?

Issue - State: open - Opened by 2302664592 9 months ago - 1 comment

#699 - AttributeError: 'NoneType' object has no attribute 'HasField'

Issue - State: open - Opened by rku1999 9 months ago - 1 comment

#698 - How to implement demo effect

Issue - State: open - Opened by yang-junhua 9 months ago - 5 comments

#697 - Extracted embedding result does not make sense

Issue - State: closed - Opened by benam2 9 months ago - 4 comments

#696 - Is there only one input shape for vit to correctly output mask？

Issue - State: open - Opened by w1005444804 9 months ago - 7 comments

GitHub / facebookresearch/segment-anything issues and pull requests