Top 11 mnn open source projects

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

✭ 3,640

python C++java CMake android deep-learning pytorch object-detection deep-neural-networks model-zoo mnn shufflenet ncnn openvino anchor-free efficientnet repvgg

Tnn

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 …

✭ 3,257

C++Objective-C++python c assembly Cuda ocr deep-learning tensorflow inference pytorch tengine face-detection tensorrt mnn coreml ncnn openvino hairsegmentaion

Mobilenet Yolo

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

✭ 1,566

c Cuda C++python CMake Batchfile deep-learning computer-vision object-detection cnn face-detection yolo yolov3 cv darknet mobilenetv2 landmark-detection landmark mnn ncnn mobilenet-yolo ncnn-model mnn-framework

Ultra Light Fast Generic Face Detector 1mb

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

✭ 6,182

python C++arm face-detection inference mnn ncnn

Mnn

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

✭ 6,284

C++c assembly python Objective-C++Cuda deep-learning machine-learning deep-neural-networks arm vulkan ml convolution embedded-devices mnn winograd-algorithm

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, MODNet, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

✭ 1,354

C++c segmentation face-recognition face-detection object-detection matting mnn ncnn retinaface onnxruntime modnet tnn nanodet yolor scrfd yolox yolox-nano yolox-tiny yolop robustvideomatting mgmatting

InferenceHelper

C++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow

✭ 142

C++CMake opencv deep-learning tensorflow inference deeplearning tensorrt mnn nnabla ncnn

Harmony

Harmony framework for connecting scRNA-seq data from discrete time points

✭ 36

Jupyter Notebook python scrna-seq mnn batch-correction scrna-seq-analysis developmental-trajecotries

YOLOv5-Lite

🍅🍅🍅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~

✭ 1,230

python C++Makefile c CMake shell pytorch transformer android-app tensorrt mnn mobilenet ncnn tflite shufflenetv2 onnxruntime yolov5 repvgg pplcnet openvivo picodet

Jetson-Nano-image

Jetson Nano image with deep learning frameworks

✭ 46

opencv deep-learning tensorflow cuda torch pytorch tegra mnn sd-card-image ncnn torchvision jetson-nano team-viewer

Peppa-Facial-Landmark-PyTorch

Facial Landmark Detection based on PyTorch

✭ 172

python pytorch face alignment landmarks facial landmark mnn onnx

1-11 of 11 mnn projects