Yucao42

g2o_pose_optimization

Use g2o to optimize the camera pose. Initial guess is from EPnP.

AES_GCM

Try to implement GCM-AES encryption algorithm on FPGA hardware and test it by software.

Line_based_BA

Using matching world-3D-to-image-2D lines to estimate the pose in C++.

image_zmq

Using zmq to transmit image/video stream.

ARC-AGI

The Abstraction and Reasoning Corpus

braft

An industrial-grade C++ implementation of RAFT consensus algorithm based on brpc, widely used inside Baidu to build highly-available distributed systems.

caffe_cpp

caffe cpp application

DeepLearning2019

Evaluation code for the final project in DS-GA 1008: Deep Learning 2019

deepstream_360_d_smart_parking_application

Describes the full end to end smart parking application that is available with DeepStream 4.0

detectron2

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

detr

End-to-End Object Detection with Transformers

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

faiss

A library for efficient similarity search and clustering of dense vectors.

FAISS_exps

FAISS KNN/ANN Experiments Pool

grpc_vas

incubator-brpc

Industrial-grade RPC framework used throughout Baidu, with 1,000,000+ instances and thousands kinds of services, called "baidu-rpc" inside Baidu.

kserve

Standardized Serverless ML Inference Platform on Kubernetes

libtorch-yolov3

A Libtorch implementation of the YOLO v3 object detection algorithm

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

models-comparison.pytorch

Code for the paper Benchmark Analysis of Representative Deep Neural Network Architectures

nexus

ng-video-lecture

nyu-latex-templates

Beamer presentation and poster template for New York University / NYU Abu Dhabi / NYU Shanghai

timely-dataflow

A modular implementation of timely dataflow in Rust

toy_mps

Check how MPS works

tracking_wo_bnw

Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"

triton-inference-server

The Triton Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

Ultra-Light-Fast-Generic-Face-Detector-1MB

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

vim_env

In convenience of vim environment setting.

Yucao42.github.io