ncnn
Mobile DL framework
An optimized framework for deploying deep learning models on mobile devices.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
20k stars
572 watching
4k forks
Language: C++
last commit: 6 days ago
Linked from 5 awesome lists
androidarm-neonartificial-intelligencecaffedarknetdeep-learninghigh-preformanceinferenceioskerasmlirmxnetncnnneural-networkonnxpytorchriscvsimdtensorflowvulkan
fffaraz/awesome-cpp
vinjn/awesome-vulkan
caerind/awesomecppgamedev
michaelxin/awesome-caffe
markusschanta/awesome-kerasRelated projects:
| Repository | Description | Stars |
|---|---|---|
| tencent/tnn | A high-performance neural network inference framework supporting various deep learning frameworks and hardware platforms. | 4,415 |
 alibaba/mnn | A lightweight deep learning framework designed for efficient inference and training on-device | 8,739 |
 moli232777144/mtcnn_ncnn | A project that builds and integrates the ncnn framework for mobile face detection on Windows and Android platforms. | 528 |
| tencent/pocketflow | A framework that automatically compresses and accelerates deep learning models to make them suitable for mobile devices with limited computational resources. | 2,788 |
 nihui/ncnn-android-styletransfer | An Android project demonstrating style transfer using the NCNN neural network library | 90 |
 xilinx/finn | Fast and scalable neural network inference framework for FPGAs. | 747 |
 sony/nnabla | A deep learning framework that provides a flexible and expressive Python API for building and training neural networks on various platforms. | 2,728 |
| nihui/ncnn-android-squeezenet | A sample Android project that uses the NCNN library for image classification on ARM-based devices. | 155 |
 xiang-wuu/ncnn-android-yolov7 | An Android implementation of object detection using Yolov7 and the ncnn neural network library | 133 |
 nilseuropa/ros_ncnn | A ROS wrapper for NCNN, allowing developers to integrate high-performance neural network inference into ROS projects | 63 |
 yangyanli/pointcnn | A deep learning framework for processing 3D point cloud data to extract relevant features for classification and segmentation tasks. | 1,382 |
 microsoft/cntk | A unified deep learning toolkit that describes neural networks as a series of computational steps via a directed graph. | 17,523 |
 taolei87/rcnn | An implementation of neural network components and optimization methods for text analysis, including rationales for neural predictions. | 355 |
 majianjia/nnom | A high-level inference Neural Network library specifically designed for microcontrollers. | 950 |
 rangilyu/nanodet | A lightweight object detection model designed for efficient inference on mobile devices and edge AI applications. | 5,769 |