MegEngine topic
MegEngine is a fast, scalable and easy-to-use deep learning framework, with auto-differentiation.
How to Contact Us
- Issue: github.com/MegEngine/MegEngine/issues
- 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
- 问题: github.com/MegEngine/MegEngine/issues
- 邮箱: [email protected]
- 论坛: discuss.megengine.org.cn
- QQ: 1029741705
资源
megcup-feedback
RAW-based blind denoising, 1st place in MegCup 2022 (Team Feedback)
basecls
A codebase & model zoo for pretrained backbone based on MegEngine.
D2C-SR
Official MegEngine implementation of ECCV2022 "D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution".
FST-Matching
Official implementation of the FST-Matching Model.
HDR-Transformer
The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer
Documentation
MegEngine Official Documentation
ECCV2022-RIFE
Official MegEngine Implementation of Real-Time Intermediate Flow Estimation for Video Frame Interpolation
examples
A set of examples around MegEngine
GyroFlow
The official MegEngine implementation of the ICCV 2021 paper: GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
ICD
This is the official implementation of the paper "Instance-conditional Knowledge Distillation for Object Detection", based on MegEngine and Pytorch.