{"id":14572429,"url":"https://github.com/jamjamjon/usls","last_synced_at":"2025-05-16T09:05:15.079Z","repository":{"id":230359067,"uuid":"779168284","full_name":"jamjamjon/usls","owner":"jamjamjon","description":"A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.","archived":false,"fork":false,"pushed_at":"2025-05-13T09:28:25.000Z","size":23492,"stargazers_count":141,"open_issues_count":4,"forks_count":20,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-05-13T10:38:45.437Z","etag":null,"topics":["clip","cuda","florence2","grounding-dino","imshow","moondream","ocr","onnx","onnxruntime","rust-yolo","sam","sapiens","smolvlm","tensorrt","yolo","yolo-rs","yolo-rust","yolov10","yolov11","yolov8"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jamjamjon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-03-29T07:36:09.000Z","updated_at":"2025-05-13T09:28:29.000Z","dependencies_parsed_at":"2024-05-11T16:28:44.146Z","dependency_job_id":"7b0a3794-f05b-4915-b15c-16d6310c824a","html_url":"https://github.com/jamjamjon/usls","commit_stats":{"total_commits":59,"total_committers":6,"mean_commits":9.833333333333334,"dds":0.2033898305084746,"last_synced_commit":"57db14ce5d04eebd51708c81b7850b078727aadd"},"previous_names":["jamjamjon/usls"],"tags_count":18,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamjamjon%2Fusls","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamjamjon%2Fusls/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamjamjon%2Fusls/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jamjamjon%2Fusls/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jamjamjon","download_url":"https://codeload.github.com/jamjamjon/usls/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254501557,"owners_count":22081528,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["clip","cuda","florence2","grounding-dino","imshow","moondream","ocr","onnx","onnxruntime","rust-yolo","sam","sapiens","smolvlm","tensorrt","yolo","yolo-rs","yolo-rust","yolov10","yolov11","yolov8"],"created_at":"2024-09-07T09:01:10.811Z","updated_at":"2025-05-16T09:05:10.044Z","avatar_url":"https://github.com/jamjamjon.png","language":"Rust","funding_links":[],"categories":["Other Versions of YOLO","Machine Learning"],"sub_categories":[],"readme":"\u003ch2 align=\"center\"\u003eusls\u003c/h2\u003e\n\n\u003cp align=\"center\"\u003e\n \u003ca href=\"https://github.com/jamjamjon/usls/actions/workflows/rust-ci.yml\"\u003e\n \u003cimg src=\"https://github.com/jamjamjon/usls/actions/workflows/rust-ci.yml/badge.svg\" alt=\"Rust Continuous Integration Badge\"\u003e\n \u003c/a\u003e\n \u003ca href='https://crates.io/crates/usls'\u003e\n \u003cimg src='https://img.shields.io/crates/v/usls.svg' alt='usls Version'\u003e\n \u003c/a\u003e\n \u003ca href='https://crates.io/crates/usls'\u003e\n \u003cimg src='https://img.shields.io/crates/msrv/usls-yellow?' alt='Rust MSRV'\u003e\n \u003c/a\u003e\n \u003ca href='https://github.com/microsoft/onnxruntime/releases'\u003e\n \u003cimg src='https://img.shields.io/badge/onnxruntime-%3E%3D%201.19.0-3399FF' alt='ONNXRuntime MSRV'\u003e\n \u003c/a\u003e\n \u003ca href='https://developer.nvidia.com/cuda-toolkit-archive'\u003e\n \u003cimg src='https://img.shields.io/badge/cuda-%3E%3D%2012.0-green' alt='CUDA MSRV'\u003e\n \u003c/a\u003e\n \u003ca href='https://developer.nvidia.com/tensorrt'\u003e\n \u003cimg src='https://img.shields.io/badge/TensorRT-%3E%3D%2012.0-0ABF53' alt='TensorRT MSRV'\u003e\n \u003c/a\u003e\n \u003ca href=\"https://crates.io/crates/usls\"\u003e\n \u003cimg alt=\"Crates.io Total Downloads\" src=\"https://img.shields.io/crates/d/usls?\u0026color=946CE6\"\u003e\n \u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n \u003ca href=\"./examples\"\u003e\n \u003cimg src=\"https://img.shields.io/badge/Examples-1A86FD?\u0026logo=anki\" alt=\"Examples\"\u003e\n \u003c/a\u003e\n \u003ca href='https://docs.rs/usls'\u003e\n \u003cimg src='https://img.shields.io/badge/Docs-usls-yellow?\u0026logo=docs.rs\u0026color=FFA200' alt='usls documentation'\u003e\n \u003c/a\u003e\n\u003c/p\u003e\n\n**usls** is a Rust library integrated with **ONNXRuntime**, offering a suite of advanced models for **Computer Vision** and **Vision-Language** tasks, including:\n\n- **YOLO Models**: [YOLOv5](https://github.com/ultralytics/yolov5), [YOLOv6](https://github.com/meituan/YOLOv6), [YOLOv7](https://github.com/WongKinYiu/yolov7), [YOLOv8](https://github.com/ultralytics/ultralytics), [YOLOv9](https://github.com/WongKinYiu/yolov9), [YOLOv10](https://github.com/THU-MIG/yolov10), [YOLO11](https://github.com/ultralytics/ultralytics), [YOLOv12](https://github.com/sunsmarterjie/yolov12)\n- **SAM Models**: [SAM](https://github.com/facebookresearch/segment-anything), [SAM2](https://github.com/facebookresearch/segment-anything-2), [MobileSAM](https://github.com/ChaoningZhang/MobileSAM), [EdgeSAM](https://github.com/chongzhou96/EdgeSAM), [SAM-HQ](https://github.com/SysCV/sam-hq), [FastSAM](https://github.com/CASIA-IVA-Lab/FastSAM)\n- **Vision Models**: [RT-DETR](https://arxiv.org/abs/2304.08069), [RTMO](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo), [Depth-Anything](https://github.com/LiheYoung/Depth-Anything), [DINOv2](https://github.com/facebookresearch/dinov2), [MODNet](https://github.com/ZHKKKe/MODNet), [Sapiens](https://arxiv.org/abs/2408.12569), [DepthPro](https://github.com/apple/ml-depth-pro), [FastViT](https://github.com/apple/ml-fastvit), [BEiT](https://github.com/microsoft/unilm/tree/master/beit), [MobileOne](https://github.com/apple/ml-mobileone)\n- **Vision-Language Models**: [CLIP](https://github.com/openai/CLIP), [jina-clip-v1](https://huggingface.co/jinaai/jina-clip-v1), [BLIP](https://arxiv.org/abs/2201.12086), [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO), [YOLO-World](https://github.com/AILab-CVC/YOLO-World), [Florence2](https://arxiv.org/abs/2311.06242), [Moondream2](https://github.com/vikhyat/moondream/tree/main)\n- **OCR Models**: [FAST](https://github.com/czczup/FAST), [DB(PaddleOCR-Det)](https://arxiv.org/abs/1911.08947), [SVTR(PaddleOCR-Rec)](https://arxiv.org/abs/2205.00159), [SLANet](https://paddlepaddle.github.io/PaddleOCR/latest/algorithm/table_recognition/algorithm_table_slanet.html), [TrOCR](https://huggingface.co/microsoft/trocr-base-printed), [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)\n\n\u003cdetails\u003e\n\u003csummary\u003eπŸ‘‰ More Supported Models\u003c/summary\u003e\n\n| Model | Task / Description | Example | CoreML | CUDA\u003cbr /\u003eFP32 | CUDA\u003cbr /\u003eFP16 | TensorRT\u003cbr /\u003eFP32 | TensorRT\u003cbr /\u003eFP16 |\n| -------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | ---------------------------- | ------ | -------------- | -------------- | ------------------ | ------------------ |\n| [BEiT](https://github.com/microsoft/unilm/tree/master/beit) | Image Classification | [demo](examples/beit) | βœ… | βœ… | βœ… | | |\n| [ConvNeXt](https://github.com/facebookresearch/ConvNeXt) | Image Classification | [demo](examples/convnext) | βœ… | βœ… | βœ… | | |\n| [FastViT](https://github.com/apple/ml-fastvit) | Image Classification | [demo](examples/fastvit) | βœ… | βœ… | βœ… | | |\n| [MobileOne](https://github.com/apple/ml-mobileone) | Image Classification | [demo](examples/mobileone) | βœ… | βœ… | βœ… | | |\n| [DeiT](https://github.com/facebookresearch/deit) | Image Classification | [demo](examples/deit) | βœ… | βœ… | βœ… | | |\n| [DINOv2](https://github.com/facebookresearch/dinov2) | VisionΒ Embedding | [demo](examples/dinov2) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv5](https://github.com/ultralytics/yolov5) | Image Classification\u003cbr /\u003eObject Detection\u003cbr /\u003eInstance Segmentation | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv6](https://github.com/meituan/YOLOv6) | Object Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv7](https://github.com/WongKinYiu/yolov7) | Object Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv8\u003cbr /\u003eYOLO11](https://github.com/ultralytics/ultralytics) | Object Detection\u003cbr /\u003eInstance Segmentation\u003cbr /\u003eImage Classification\u003cbr /\u003eOriented Object Detection\u003cbr /\u003eKeypoint Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv9](https://github.com/WongKinYiu/yolov9) | Object Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv10](https://github.com/THU-MIG/yolov10) | Object Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLOv12](https://github.com/sunsmarterjie/yolov12) | Object Detection | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [RT-DETR](https://github.com/lyuwenyu/RT-DETR) | Object Detection | [demo](examples/rtdetr) | βœ… | βœ… | βœ… | | |\n| [RF-DETR](https://github.com/roboflow/rf-detr) | Object Detection | [demo](examples/rfdetr) | βœ… | βœ… | βœ… | | |\n| [PP-PicoDet](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.8/configs/picodet) | Object Detection | [demo](examples/picodet-layout) | βœ… | βœ… | βœ… | | |\n| [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO) | Object Detection | [demo](examples/picodet-layout) | βœ… | βœ… | βœ… | | |\n| [D-FINE](https://github.com/manhbd-22022602/D-FINE) | Object Detection | [demo](examples/d-fine) | βœ… | βœ… | βœ… | | |\n| [DEIM](https://github.com/ShihuaHuang95/DEIM) | Object Detection | [demo](examples/deim) | βœ… | βœ… | βœ… | | |\n| [RTMO](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo) | Keypoint Detection | [demo](examples/rtmo) | βœ… | βœ… | βœ… | ❌ | ❌ |\n| [SAM](https://github.com/facebookresearch/segment-anything) | Segment Anything | [demo](examples/sam) | βœ… | βœ… | βœ… | | |\n| [SAM2](https://github.com/facebookresearch/segment-anything-2) | Segment Anything | [demo](examples/sam) | βœ… | βœ… | βœ… | | |\n| [MobileSAM](https://github.com/ChaoningZhang/MobileSAM) | Segment Anything | [demo](examples/sam) | βœ… | βœ… | βœ… | | |\n| [EdgeSAM](https://github.com/chongzhou96/EdgeSAM) | Segment Anything | [demo](examples/sam) | βœ… | βœ… | βœ… | | |\n| [SAM-HQ](https://github.com/SysCV/sam-hq) | Segment Anything | [demo](examples/sam) | βœ… | βœ… | βœ… | | |\n| [FastSAM](https://github.com/CASIA-IVA-Lab/FastSAM) | Instance Segmentation | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [YOLO-World](https://github.com/AILab-CVC/YOLO-World) | Open-Set Detection With Language | [demo](examples/yolo) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO) | Open-Set Detection With Language | [demo](examples/grounding-dino) | βœ… | βœ… | βœ… | | |\n| [CLIP](https://github.com/openai/CLIP) | Vision-Language Embedding | [demo](examples/clip) | βœ… | βœ… | βœ… | ❌ | ❌ |\n| [jina-clip-v1](https://huggingface.co/jinaai/jina-clip-v1) | Vision-Language Embedding | [demo](examples/clip) | βœ… | βœ… | βœ… | ❌ | ❌ |\n| [BLIP](https://github.com/salesforce/BLIP) | Image Captioning | [demo](examples/blip) | βœ… | βœ… | βœ… | ❌ | ❌ |\n| [DB(PaddleOCR-Det)](https://arxiv.org/abs/1911.08947) | Text Detection | [demo](examples/db) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [FAST](https://github.com/czczup/FAST) | Text Detection | [demo](examples/fast) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [LinkNet](https://arxiv.org/abs/1707.03718) | Text Detection | [demo](examples/linknet) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [SVTR(PaddleOCR-Rec)](https://arxiv.org/abs/2205.00159) | Text Recognition | [demo](examples/svtr) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [SLANet](https://paddlepaddle.github.io/PaddleOCR/latest/algorithm/table_recognition/algorithm_table_slanet.html) | Tabel Recognition | [demo](examples/slanet) | βœ… | βœ… | βœ… | | |\n| [TrOCR](https://huggingface.co/microsoft/trocr-base-printed) | Text Recognition | [demo](examples/trocr) | βœ… | βœ… | βœ… | | |\n| [YOLOPv2](https://arxiv.org/abs/2208.11434) | Panoptic Driving Perception | [demo](examples/yolop) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [DepthAnything v1\u003cbr /\u003eDepthAnything v2](https://github.com/LiheYoung/Depth-Anything) | Monocular Depth Estimation | [demo](examples/depth-anything) | βœ… | βœ… | βœ… | ❌ | ❌ |\n| [DepthPro](https://github.com/apple/ml-depth-pro) | Monocular Depth Estimation | [demo](examples/depth-pro) | βœ… | βœ… | βœ… | | |\n| [MODNet](https://github.com/ZHKKKe/MODNet) | Image Matting | [demo](examples/modnet) | βœ… | βœ… | βœ… | βœ… | βœ… |\n| [Sapiens](https://github.com/facebookresearch/sapiens/tree/main) | Foundation for Human Vision Models | [demo](examples/sapiens) | βœ… | βœ… | βœ… | | |\n| [Florence2](https://arxiv.org/abs/2311.06242) | a Variety of Vision Tasks | [demo](examples/florence2) | βœ… | βœ… | βœ… | | |\n| [Moondream2](https://github.com/vikhyat/moondream/tree/main) | Open-Set Object Detection\u003cbr /\u003eOpen-Set Keypoints Detection\u003cbr /\u003eImageΒ Caption\u003cbr /\u003eVisual Question Answering | [demo](examples/moondream2) | βœ… | βœ… | βœ… | | |\n| [OWLv2](https://huggingface.co/google/owlv2-base-patch16-ensemble) | Open-Set Object Detection | [demo](examples/owlv2) | βœ… | βœ… | βœ… | | |\n| [SmolVLM(256M, 500M)](https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct) | Visual Question Answering | [demo](examples/smolvlm) | βœ… | βœ… | βœ… | | |\n\n\u003c/details\u003e\n\n## ⛳️ Cargo Features\n\nBy default, **none of the following features are enabled**. You can enable them as needed:\n\n- **`auto`**: Automatically downloads prebuilt ONNXRuntime binaries from Pyke’s CDN for supported platforms.\n\n - If disabled, you'll need to [compile `ONNXRuntime` from source](https://github.com/microsoft/onnxruntime) or [download a precompiled package](https://github.com/microsoft/onnxruntime/releases), and then [link it manually](https://ort.pyke.io/setup/linking).\n\n \u003cdetails\u003e\n \u003csummary\u003eπŸ‘‰ For Linux or macOS Users\u003c/summary\u003e\n\n - Download from the [Releases page](https://github.com/microsoft/onnxruntime/releases).\n - Set up the library path by exporting the `ORT_DYLIB_PATH` environment variable:\n ```shell\n export ORT_DYLIB_PATH=/path/to/onnxruntime/lib/libonnxruntime.so.1.20.1\n ```\n\n \u003c/details\u003e\n- **`ffmpeg`**: Adds support for video streams, real-time frame visualization, and video export.\n\n - Powered by [video-rs](https://github.com/oddity-ai/video-rs) and [minifb](https://github.com/emoon/rust_minifb). For any issues related to `ffmpeg` features, please refer to the issues of these two crates.\n- **`cuda`**: Enables the NVIDIA TensorRT provider.\n- **`trt`**: Enables the NVIDIA TensorRT provider.\n- **`mps`**: Enables the Apple CoreML provider.\n\n## 🎈 Example\n\n* **Using `CUDA`**\n\n ```\n cargo run -r -F cuda --example yolo -- --device cuda:0\n ```\n* **Using Apple `CoreML`**\n\n ```\n cargo run -r -F mps --example yolo -- --device mps\n ```\n* **Using `TensorRT`**\n\n ```\n cargo run -r -F trt --example yolo -- --device trt\n ```\n* **Using `CPU`**\n\n ```\n cargo run -r --example yolo\n ```\n\nAll examples are located in the [examples](./examples/) directory.\n\n## πŸ₯‚ Integrate Into Your Own Project\n\nAdd `usls` as a dependency to your project's `Cargo.toml`\n\n```Shell\ncargo add usls -F cuda\n```\n\nOr use a specific commit:\n\n```Toml\n[dependencies]\nusls = { git = \"https://github.com/jamjamjon/usls\", rev = \"commit-sha\" }\n```\n\n## πŸ₯³ If you find this helpful, please give it a star ⭐\n\n## πŸ“Œ License\n\nThis project is licensed under [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjamjamjon%2Fusls","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjamjamjon%2Fusls","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjamjamjon%2Fusls/lists"}