#大语言模型#MNN是一个轻量级的深度神经网络引擎,支持深度学习的推理与训练。适用于服务器/个人电脑/手机/嵌入式各类设备。目前,MNN已经在阿里巴巴的手机淘宝、手机天猫、优酷等30多个App中使用,覆盖直播、短视频、搜索推荐、商品图像搜索、互动营销、权益发放、安全风控等场景。
#人脸识别# 💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
#安卓#NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
翻译 - ⚡超级快速,轻巧的无锚物体检测模型。 1.8仅1.8mb并在手机上运行97FPS🔥
#人脸识别#由腾讯优图实验室开源的高性能、轻量级神经网络推理框架,同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。
🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉
翻译 - 🍅🍅A lite C++ 工具包,包含具有 ONNXRuntime、NCNN、MNN 和 TNN 的出色 AI 模型。 YOLOX、YOLOP、YOLOv5、YOLOR、NanoDet、YOLOX、SCRFD、YOLOX。 MNN、NCNN、TNN、ONNXRuntime、CPU/GPU。
🍅🍅🍅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~
翻译 - shufflev2-yolov5:更轻、更快、更容易部署。由yolov5进化而来,模型大小只有1.7M(int8)和3.3M(fp16)。当输入大小为320×320时,它可以在树莓派4B上达到10+ FPS~
#人脸识别#MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
翻译 - MobileNetV2-YoloV3-Nano:0.5BFlops 3MB HUAWEI P40:6ms / img,YoloFace-500k:0.1Bflops500KB:fire :: fire :: fire:
llm deploy project based mnn. This project has merged into MNN.
#安卓#Sharpen your low-resolution pictures with the power of AI upscaling
#安卓#Stable Diffusion in NCNN with c++, supported txt2img and img2img
nndeploy is an end-to-end model inference and deployment framework. It aims to provide users with a powerful, easy-to-use, high-performance, and mainstream framework compatible model inference and dep...
A toolbox for deep learning model deployment using C++ YoloX | YoloV7 | YoloV8 | Gan | OCR | MobileVit | Scrfd | MobileSAM | StableDiffusion
#计算机科学#an edge-real-time anchor-free object detector with decent performance
#计算机科学#C++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow
alibaba MNN, mobilenet classifier, centerface detecter, ultraface detecter, pfld landmarker and zqlandmarker, mobilefacenet
#计算机科学#在Android使用深度学习模型实现图像识别,本项目提供了多种使用方式,使用到的框架如下:Tensorflow Lite、Paddle Lite、MNN、TNN
#人脸识别#Raspberry Pi 4 Buster 64-bit OS with deep learning examples