YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
-
Updated
May 15, 2024 - Python
MegEngine is a fast, scalable and easy-to-use deep learning framework, with auto-differentiation.
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。
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 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
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
MegEngine Official Documentation
Efficient ML solution for long-tailed demands.
Python package containing all custom layers used in Neural Networks (Compatible with PyTorch, TensorFlow and MegEngine)
Official MegEngine implementation of RepLKNet
The official MegEngine implementation of the ECCV 2022 paper: Ghost-free High Dynamic Range Imaging with Context-aware Transformer
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)
This is the official implementation of the paper "Instance-conditional Knowledge Distillation for Object Detection", based on MegEngine and Pytorch.
The official MegEngine implementation of the ICCV 2021 paper: GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning
OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration, ICCV 2021, MegEngine implementation.
An end to end ASR Transformer model training repo
A codebase & model zoo for pretrained backbone based on MegEngine.
Created by Megvii
Latest release 6 months ago