MegEngine
MegEngine is a fast, scalable and easy-to-use deep learning framework, with auto-differentiation.
How to Contact Us
- Email: [email protected]
- Forum: discuss.megengine.org.cn
- QQ Group: 1029741705
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
- QQ: 1029741705
资源
Here are 66 public repositories matching this topic...
旷视AI智慧交通开源赛道 **非官方**第二名解决方案(初赛/决赛第二名, 0.61447/0.58183)
-
Updated
Sep 29, 2021 - Python
Swin-Transformer implementation in MegEngine. This is a showcase for training on GPU with less memory by leveraging MegEngine DTR technique.
-
Updated
Oct 19, 2021 - Python
An end to end ASR Transformer model training repo
-
Updated
Dec 8, 2021 - Python
Examples for using MegEngine cpp API for model training, which support Linux, Windows, Android, Linux_arm and IOS.
-
Updated
Dec 27, 2021 - C++
OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration, ICCV 2021, MegEngine implementation.
-
Updated
Feb 6, 2022 - Python
Official MegEngine implementation of RepLKNet
-
Updated
Apr 17, 2022 - Python
-
Updated
Apr 23, 2022 - Python
Light parameters raw image denoising, 2nd place in MegCup 2022
-
Updated
Apr 23, 2022 - Python
RAW-based blind denoising, 1st place in MegCup 2022 (Team Feedback)
-
Updated
Apr 27, 2022 - Python
RAW-based blind denoising, 3rd place in MegCup 2022 (Team Feedforward)
-
Updated
Apr 28, 2022 - Python
Created by Megvii
Latest release 10 months ago
- Followers
- 7 followers
- Repository
- MegEngine/MegEngine
- Website
- www.megengine.org.cn