Yu Yang's starred repositories
SQuAD-explorer
Visually Explore the Stanford Question Answering Dataset
ByteTransformer
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
FasterTransformer
Transformer related optimization, including BERT, GPT
flash-attention
Fast and memory-efficient exact attention
deep-high-resolution-net.pytorch
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
lightweight-human-pose-estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
movenet.pytorch
A Pytorch implementation of MoveNet from Google. Include training code and pre-trained model.
pytorch-YOLOv4
PyTorch ,ONNX and TensorRT implementation of YOLOv4
urban-object-detection
PyTorch implementation of an urban object detection model.
hpc-course-examples
Examples for HPC course
Algorithm_Interview_Notes-Chinese
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
CppCon2019
Slides and other materials from CppCon 2019
FeatherCNN
FeatherCNN is a high performance inference engine for convolutional neural networks.
ComputeLibrary
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
LFFD-A-Light-and-Fast-Face-Detector-for-Edge-Devices
A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......
interview_internal_reference
2019年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。
cs_threadpool_epoll_mq
基于线程池、消息队列和epoll模型实现并发服务器架构
xv6-chinese
中文版的 MIT xv6 文档