YangXiuyu's repositories
CourseNotes
CourseNotes at SJTU Information-Engineering.
mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
Openclip-ait
Accelerate CLIP via AITemplate
Openclip-CUDAGraph
Using CUDAGraph to accelerate the CLIP
Openclip-flashattn
Integrate FlashAttention into CLIP Model
Small-3D-Semantic-Segmentation-model
Small-3D-Semantic-Segmentation-model
AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
JDet
JDet is an object detection benchmark based on Jittor. Mainly focus on aerial image object detection (oriented object detection).
annlite
⚡ A fast embedded library for approximate nearest neighbor search
clash-verge
A Clash GUI based on tauri. Supports Windows, macOS and Linux.
clash-verge-rev
Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)
clip-as-service
🏄 Embed/reason/rank images and sentences with CLIP models
Det3D
A general 3D object detection codebse.
idisc
iDisc: Internal Discretization for Monocular Depth Estimation [CVPR 2023]
MVDiffusion
MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)
nerfstudio
A collaboration friendly studio for NeRFs
nobelium
A static blog build on top of Notion and NextJS, deployed on Vercel.
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
text2room
Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).
towhee
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.
UniAD
[CVPR 2023 Best Paper] Planning-oriented Autonomous Driving
VoxSeT
Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR 2022)