MNN
Deep learning framework
A lightweight deep learning framework developed by Alibaba for efficient inference and training of neural networks on-device.
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
9k stars
198 watching
2k forks
Language: C++
last commit: about 1 month ago
Linked from 1 awesome list
armconvolutiondeep-learningdeep-neural-networksembedded-devicesmachine-learningmlmnnvulkanwinograd-algorithm
Related projects:
Repository | Description | Stars |
---|---|---|
tencent/tnn | A high-performance neural network inference framework supporting various deep learning frameworks and hardware platforms. | 4,435 |
tencent/ncnn | An optimized framework for deploying deep learning models on mobile devices. | 20,655 |
microsoft/mmdnn | A toolset to convert and manage deep learning models across multiple frameworks. | 5,802 |
alirezadir/production-level-deep-learning | A guide to building production-ready deep learning systems for real-world applications | 4,371 |
jolibrain/deepdetect | A machine learning API and server written in C++ that supports multiple deep learning libraries and provides a flexible interface for building and deploying machine learning models. | 2,520 |
apple/corenet | A deep neural network toolkit allowing researchers and engineers to train various models | 6,997 |
xmartlabs/bender | An abstraction layer for building and running neural networks on iOS using MetalPerformanceShaders and pre-trained models. | 1,798 |
nlintz/tensorflow-tutorials | A collection of tutorials teaching deep learning with TensorFlow using Jupyter Notebooks | 6,003 |
weiliu89/caffe | A deep learning framework for rapid prototyping and production of computer vision applications | 4,770 |
xiaomi/mace | A framework for deep learning inference on mobile devices | 4,949 |
aksnzhy/xlearn | A high-performance machine learning package with linear models and factorization machines. | 3,087 |
qwenlm/qwen | This repository provides large language models and chat capabilities based on pre-trained Chinese models. | 14,797 |
tflearn/tflearn | A high-level API for deep learning that builds upon TensorFlow | 9,621 |
mg2033/shufflenet | An implementation of a computationally efficient deep neural network architecture designed for mobile devices with limited computing power. | 383 |
tusen-ai/simpledet | A framework for object detection and instance recognition with high-performance training capabilities | 3,085 |