⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
OpenMLDB是一个开源机器学习数据库，面向机器学习应用提供正确、高效数据供给。
OpenVINO allows developers to deploy pre-trained deep learning models through a high-level C++ Inference Engine API integrated with application logic.
Ascend TensorFlow Adapter
深度学习模型压缩算法库，支持网络结构搜索、剪枝、蒸馏等主流技术方向，为 OpenMMLab 其他算法库提供即插即用、可自由组合的模型压缩算法，让用户更简单更快速地实现模型轻量化。
OPT（Omni-Perception Pre-Trainer）是全场景感知预训练模型的简称，中文名字叫紫东太初，是中科院自动化和华为联合研发的多模态预训练模型，本仓是紫东太初十亿参数级别模型的MindSpore版本代码，包含预训练模型及多个下游任务模型。
