MegEngine
MegEngine is a fast, scalable and easy-to-use deep learning framework, with auto-differentiation.
How to Contact Us
Resources
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架，具备训练推理一体、全平台高效支持和动静结合的训练能力 3 大核心优势，可帮助企业与开发者大幅节省产品从实验室原型到工业部署的流程，真正实现小时级的转化能力。
联系我们
资源
Here are 68 public repositories matching this topic...
论文Probabilistic Anchor Assignment with IoU Prediction for Object Detection的Megengine实现
-
Updated
Aug 23, 2022 - Python
The MegEngine implementation of IBNNet(Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net)
-
Updated
Aug 22, 2022 - Python
MegEngine implementation of Diffusion Models.
-
Updated
Aug 8, 2022 - Python
论文OTA: Optimal Transport Assignment for Object Detection的Megengine实现
-
Updated
Aug 23, 2022 - Python
论文FishNet: a versatile backbone for image, region, and pixel level prediction的Megengine实现
-
Updated
Aug 23, 2022 - Python
MegBox is an easy-to-use, well-rounded and safe toolbox of MegEngine. Aim to imporving usage experience and speeding up develop process.
-
Updated
Apr 9, 2023 - Python
Wide-Residual-Networks (MegEngine implementation）
-
Updated
Aug 12, 2022 - Python
-
Updated
Aug 18, 2022 - Python
Stabilize video footage using gyroscopic sensor data with this cross-platform, open-source tool.
-
Updated
Oct 5, 2026
Created by Megvii
Latest release almost 3 years ago
- Followers
- 7 followers
- Repository
- MegEngine/MegEngine
- Website
- github.com/topics/megengine