Pinned Repositories
BiFormer
[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"
CNN-CBIR
Content based image retrieval, instance search (examplar object detection) using CNN, especially VGG-RMAC feature. Implemented with pytorch.
docker-cuda-codeserver
Docker code server with CUDA development environment.
FDRNet
Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"
GLMix
[NeurIPS 2024] official code release for our paper "Revisiting the Integration of Convolution and Attention for Vision Backbone".
plcc
Plane constraint based Lidar-Camera Calibration
realsense_kinect_fusion_demo
KinectFusion with realsense RGBD camera demo. It's based on OpenCV4 KinFu API.
segformer.pure
A cleaned version of official SegFormer. It removes dependency on MMCV and MMSegmentation, which use deep wrapings.
SIFT-BOW-CBIR
content based image retrieval using SIFT-BOW feature.
vllm-ra
[ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
rayleizhu's Repositories
rayleizhu/BiFormer
[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"
rayleizhu/vllm-ra
[ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
rayleizhu/GLMix
[NeurIPS 2024] official code release for our paper "Revisiting the Integration of Convolution and Attention for Vision Backbone".
rayleizhu/CNN-CBIR
Content based image retrieval, instance search (examplar object detection) using CNN, especially VGG-RMAC feature. Implemented with pytorch.
rayleizhu/FDRNet
Code for our ICCV 2021 paper "Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting"
rayleizhu/segformer.pure
A cleaned version of official SegFormer. It removes dependency on MMCV and MMSegmentation, which use deep wrapings.
rayleizhu/realsense_kinect_fusion_demo
KinectFusion with realsense RGBD camera demo. It's based on OpenCV4 KinFu API.
rayleizhu/SIFT-BOW-CBIR
content based image retrieval using SIFT-BOW feature.
rayleizhu/pomegranate
Fast, flexible and easy to use probabilistic modelling in Python.
rayleizhu/docker-cuda-codeserver
Docker code server with CUDA development environment.
rayleizhu/awsome-cuda-attention
Collection of effcient implementations of attention with CUDA
rayleizhu/CSCI5390-Nbody
CUHK CSCI5390 course project
rayleizhu/plcc
Plane constraint based Lidar-Camera Calibration
rayleizhu/Sound-Effect-Tagging
sound effect tagging using machine learning
rayleizhu/Alexnet-cntk-and-mxnet
this repo conatins implementations of Alexnet with cntk and mxnet
rayleizhu/cs344
Introduction to Parallel Programming class code
rayleizhu/detrex
detrex is a research platform for Transformer-based Instance Recognition algorithms including DETR (ECCV 2020), Deformable-DETR (ICLR 2021), Conditional-DETR (ICCV 2021), DAB-DETR (ICLR 2022), DN-DETR (CVPR 2022), DINO (ICLR 2023), H-DETR (arXiv 2022), MaskDINO (arXiv 2022), etc.
rayleizhu/blog.old
my blog repo
rayleizhu/cutlass
CUDA Templates for Linear Algebra Subroutines
rayleizhu/EpipolarGeometry-OpenCV
rayleizhu/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
rayleizhu/hexo-theme-next
Elegant and powerful theme for Hexo.
rayleizhu/HuemanGist
child theme of wordpress theme Hueman: Demo: http://rayleizhu.com
rayleizhu/MyArxivColander
My customized arxiv colander.
rayleizhu/OSExperiment
Operating System Experiments of DLUT
rayleizhu/PlantPathology2020
Kaggle Plant Pathology 2020 - FGVC7 Competetion, https://www.kaggle.com/c/plant-pathology-2020-fgvc7/overview
rayleizhu/rayleizhu.github.io
My personal website (rayleizhu.github.io). The blog site is rayleizhu.github.io/blog
rayleizhu/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.