#ncnn Repositories
Discover 30 active open source GitHub repositories tagged with #ncnn, accumulating 124,366 total stars (averaging 4,145 stars per project). Leading this topic is Tencent/ncnn with 24,082 stars.
30 repositories total
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.
Ultra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, tnn inference (dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)), total model size only 4.7M
Convert AI papers to GUI, Make it easy and convenient for everyone to use artificial intelligence technology. ่ฎฉๆฏไธชไบบ้ฝ็ฎๅๆนไพฟ็ไฝฟ็จๅๆฒฟไบบๅทฅๆบ่ฝๆๆฏ
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
NanoDet-PlusโกSuper fast and lightweight anchor-free object detection model. ๐ฅOnly 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone๐ฅ
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile, desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts
A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion.
waifu2x converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan
Good projects for campus recruitment, autumn recruitment, spring recruitment, internships! Guiding you to implement a high-performance deep learning inference library from scratch, supporting inference for large models like llama2, Unet, YoloV5, Resnet, etc. Implement a high-performance deep learning inference library step by step
๐ ๐ ๐ YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
An Android application for super-resolution & interpolation. Contains RealSR-NCNN, SRMD-NCNN, RealCUGAN-NCNN, Real-ESRGAN-NCNN, Waifu2x-NCNN, Anime4kcpp, nearest, bilinear, bicubic, AVIR...
Flowframes Windows GUI for video interpolation using DAIN (NCNN) or RIFE (CUDA/NCNN)
Local Android file converter built with Kotlin and Jetpack Compose. Convert files on device, with no ads, accounts, or upload-based fallback.
NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
Any source. One real-time GPU enhancement pipeline. ยท video enhancer ยท gpu video ยท real-time video enhancement ยท hdr ยท super-resolution ยท game-streaming ยท moonlight ยท dolby-vision ยท frame-interpolation ยท video-player ยท media-player ยท video-super-resolution ยท video-processing ยท upscaling ยท rife ยท vulkan ยท nvidia ยท windows ยท video-enhancement ยท ncnn
RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+.
Video Frame Interpolation & Super Resolution using NVIDIA's TensorRT & Tencent's NCNN inference, beautifully crafted and packaged into a single app
yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.
A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion
๐ฅ๐ฅ๐ฅJava code implementation to call RapidOCR (based on PaddleOCR), adapted for Mac, Win, Linux, supporting the latest PP-OCRv4
Frequently Asked Questions
What is the most popular #ncnn repository on GitHub?
The top ranked open source #ncnn project on GitHub is Tencent/ncnn with 24,082 stars. ncnn is a high-performance neural network inference framework optimized for the mobile platform
Which programming languages are most used in #ncnn repositories?
Among the top ranked #ncnn projects on GitHub, the most common programming languages are C++, Python, C, Jupyter Notebook.
How is the #ncnn repository ranking calculated?
We track 30 active open source repositories tagged with #ncnn (500+ stars), totaling 124,366 stars with an average of 4,145 stars per repository. Rankings update daily from the GitHub API.