Trending repositories for topic onnx
Unified framework for building enterprise RAG pipelines with small, specialized models
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Visualizer for neural network, deep learning and machine learning models
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
Effortless data labeling with AI support from Segment Anything and other awesome models.
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
Open source real-time translation app for Android that runs locally
A collection of pre-trained, state-of-the-art models in the ONNX format
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
A collection of sample programs, notebooks, and tools which highlight the power of the MAX Platform
Effortless data labeling with AI support from Segment Anything and other awesome models.
A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local embedding solution, built in rust.
Python scripts performing Instance Segmentation using the YOLOv8 model in ONNX.
The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.
Samples code for world class Artificial Intelligence SoCs for computer vision applications.
Unified framework for building enterprise RAG pipelines with small, specialized models
Visualizer for neural network, deep learning and machine learning models
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
Effortless data labeling with AI support from Segment Anything and other awesome models.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Open source real-time translation app for Android that runs locally
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
A collection of pre-trained, state-of-the-art models in the ONNX format
Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR
Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;
Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.
Lightweight & fast OCR models for license plate text recognition.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
Unified framework for building enterprise RAG pipelines with small, specialized models
A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local embedding solution, built in rust.
YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose Estimation in both images and videos.
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference
Python scripts performing Instance Segmentation using the YOLOv8 model in ONNX.
A utility to inspect, validate, sign and verify machine learning model files.
Unified framework for building enterprise RAG pipelines with small, specialized models
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
Visualizer for neural network, deep learning and machine learning models
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Effortless data labeling with AI support from Segment Anything and other awesome models.
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Open source real-time translation app for Android that runs locally
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
A collection of pre-trained, state-of-the-art models in the ONNX format
Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
CodeProject.AI Server is a self contained service that software developers can include in, and distribute with, their applications in order to augment their apps with the power of AI.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR
Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;
ONNX-backed array library that is compliant with the Array API standard.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera
Unified framework for building enterprise RAG pipelines with small, specialized models
Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
Lightweight & fast OCR models for license plate text recognition.
Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.
A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.
ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference
A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local embedding solution, built in rust.
CodeProject.AI Server is a self contained service that software developers can include in, and distribute with, their applications in order to augment their apps with the power of AI.
A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion
Python scripts performing optical flow estimation using the NeuFlowV2 model in ONNX.
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
🚀 你的YOLO部署神器。TensorRT Plugin、CUDA Kernel、CUDA Graphs三管齐下，享受闪电般的推理速度。| Your YOLO Deployment Powerhouse. With the synergy of TensorRT Plugins, CUDA Kernels, and CUDA Graphs, experience lightning-fast i...
AI Productivity Tool - Free and open-source, enhancing user productivity while ensuring privacy and data security. It provides efficient and convenient AI solutions, including but not limited to: buil...
The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
A collection of sample programs, notebooks, and tools which highlight the power of the MAX Platform
A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local embedding solution, built in rust.
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀
Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;
Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
ComfyUI Depth Anything (v1/v2) Tensorrt Custom Node (up to 14x faster)
Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
SafeDriveVision is a computer vision project aimed at enhancing road safety. This project leverages deep learning models to detect and alert in real-time the dangerous behaviors of drivers, such as us...
A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models.
Open source real-time translation app for Android that runs locally
Unified framework for building enterprise RAG pipelines with small, specialized models
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Visualizer for neural network, deep learning and machine learning models
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
Effortless data labeling with AI support from Segment Anything and other awesome models.
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
ncnn is a high-performance neural network inference framework optimized for the mobile platform
A collection of pre-trained, state-of-the-art models in the ONNX format
Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.
🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
A collection of sample programs, notebooks, and tools which highlight the power of the MAX Platform
Open source real-time translation app for Android that runs locally
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀
UniSim is a package for efficient similarity computation, fuzzy matching, and clustering of data.
Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.
ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
Unified framework for building enterprise RAG pipelines with small, specialized models
Python scripts for the Segment Anythin 2 (SAM2) model in ONNX
ComfyUI Depth Anything (v1/v2) Tensorrt Custom Node (up to 14x faster)
Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 ser...
Universal Second Eye for Gamers with Impairments (Universal AI Aim Aligner - ONNX/YOLOv8 - C#)
👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
GUI for upscaling ONNX models with NVIDIA TensorRT and Vapoursynth
A library for training, compressing and deploying computer vision models (including ViT) with edge devices