FastSAM
MobileSAM

FastSAM | MobileSAM | |
---|---|---|
6 | 6 | |
7,688 | 4,978 | |
1.1% | 1.1% | |
7.0 | 4.4 | |
7 months ago | 3 months ago | |
Python | Jupyter Notebook | |
GNU Affero General Public License v3.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FastSAM
MobileSAM
-
SamGIS - Segment Anything applied to GIS
it instantiates a MobileSam model instance if not already created using OnnxRuntime as runtime
- SamGIS - Segment Anything adattato al GIS
-
EfficientSAM
https://github.com/ChaoningZhang/MobileSAM was the previous attempt at distilling the large image encoder used by SAM.
-
AnyLabeling Auto-labeling with MobileSAM - the newest and fastest variant of Segment Anything
MobileSAM repo: https://github.com/ChaoningZhang/MobileSAM.
-
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
Highlight: The training of MobileSAM can be completed on a single GPU within less than one day. MobileSAM is 60+ times smaller yet performs on par with the original SAM. For inference speed, Compared with the concurrent FastSAM, our MobileSAM with a superior performance is 7 times smaller and 4 times faster, making it more suitable for mobile applications. The code for MobileSAM project is provided at https://github.com/ChaoningZhang/MobileSAM.
-
Fast Segment Anything (40ms/image)
lmao you called it FasterSAM
What are some alternatives?
sd-webui-inpaint-anything - Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.
anylabeling - Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
background-removal-js - Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
EfficientSAM - EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
xgen - Salesforce open-source LLMs with 8k sequence length.
parquet-format - Apache Parquet Format
samexporter - Export Segment Anything Models to ONNX
papyrus - A simple paper backup tool for GnuPG or SSH keys
sam_onnx_full_export - This repository shows how to solve ONNX export issue in Segment Anything model
wizmap - Explore and interpret large embeddings in your browser with interactive visualization! 📍
samgis-be - SamGIS can do machine learning-based (Segment Anything by Meta - Facebook) image segmentation tasks applied to GIS and geo data (there is also a SPA frontend similar to https://github.com/trincadev/samgis-fe used on HuggingFace)
