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
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
MegEngine
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
Echo
Python package containing all custom layers used in Neural Networks (Compatible with PyTorch, TensorFlow and MegEngine)
MegFlow
Efficient ML solution for long-tailed demands.
CREStereo
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
RepLKNet
Official MegEngine implementation of RepLKNet
PMRID
ECCV2020 - Practical Deep Raw Image Denoising on Mobile Devices
NBNet
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
YOLOX
MegEngine implementation of YOLOX