ncnn

Star

Here are 238 public repositories matching this topic...

Tencent / ncnn

Star

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Updated Dec 30, 2022
C++

DayBreak-u / chineseocr_lite

Star

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

ocr pytorch ncnn

Updated Nov 22, 2022
C++

AaronFeng753 / Waifu2x-Extension-GUI

Star

Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.

Updated Jan 2, 2023
C++

Megvii-BaseDetection / YOLOX

Star

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

deep-learning pytorch yolo object-detection tensorrt ncnn onnx yolov3 openvino megengine yolox

Updated Dec 29, 2022
Python

Baiyuetribe / paper2gui

Star

Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术

ncnn ncnn-model waifu2x-gui dain noveria gfpgan animegan2 rife-gui microsoft-tts huoshan-tts realesrganv2-gu realcugan-gui dain-gui stable-diffusion realcugan-pro

Updated Dec 13, 2022
Jupyter Notebook

Linzaer / Ultra-Light-Fast-Generic-Face-Detector-1MB

Star

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

arm inference face-detection mnn ncnn

Updated Feb 10, 2022
Python

k4yt3x / video2x

Star

A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.

python machine-learning video neural-network vulkan waifu2x qt5 super-resolution upscaling ncnn video-enlarger srmd anime4k realsr rife

Updated Nov 13, 2022
Python

RangiLyu / nanodet

Star

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

android deep-neural-networks deep-learning model-zoo pytorch object-detection mnn shufflenet ncnn openvino anchor-free efficientnet nanodet repvgg nanodet-plus

Updated Dec 22, 2022
Python

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 …

ocr deep-learning tensorflow inference pytorch tengine face-detection tensorrt mnn coreml ncnn openvino hairsegmentaion

Updated Dec 31, 2022
C++

nihui / waifu2x-ncnn-vulkan

Star

waifu2x converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan

windows macos linux amd gpu vulkan intel waifu2x nvidia ncnn

Updated Jan 1, 2023
C

jolibrain / deepdetect

Star

Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

machine-learning caffe deep-learning time-series gpu rest-api pytorch xgboost image-classification image-search object-detection image-segmentation tsne neural-nets tensorrt ncnn tensorrt-conversion tensorrt-inference

Updated Dec 29, 2022
C++

DefTruth / lite.ai.toolkit

Star

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv5. MNN, NCNN, TNN, ONNXRuntime.

Updated Oct 16, 2022
C++

dog-qiuqiu / MobileNet-Yolo

Star

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥

computer-vision deep-learning cv cnn yolo face-detection object-detection landmark-detection darknet landmark mnn ncnn mobilenetv2 yolov3 mobilenet-yolo ncnn-model mnn-framework

Updated Feb 6, 2021
C

open-mmlab / mmdeploy

Star

OpenMMLab Model Deployment Framework

sdk computer-vision deep-learning deployment pytorch tensorrt ncnn onnx model-converter openvino mmdetection onnxruntime mmsegmentation pplnn

Updated Dec 31, 2022
Python

ppogg / YOLOv5-Lite

Star

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~