Austin Xiao's Projects
CDF SIG MLOps
[CVPR-2022] Official implementation for "Knowledge Distillation with the Reused Teacher Classifier".
Sorting Google Scholar search results based on the number of citations
Python library for downloading, loading & working with sound datasets
:sound: spafe: Simplified Python Audio Features Extraction
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
A Pytorch implementation of the paper : SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification
spring boot demo 是一个用来深度学习并实战 spring boot 的项目,目前总共包含 65 个集成demo,已经完成 53 个。 该项目已成功集成 actuator(监控)、admin(可视化监控)、logback(日志)、aopLog(通过AOP记录web请求日志)、统一异常处理(json级别和页面级别)、freemarker(模板引擎)、thymeleaf(模板引擎)、Beetl(模板引擎)、Enjoy(模板引擎)、JdbcTemplate(通用JDBC操作数据库)、JPA(强大的ORM框架)、mybatis(强大的ORM框架)、通用Mapper(快速操作Mybatis)、PageHelper(通用的Mybatis分页插件)、mybatis-plus(快速操作Mybatis)、BeetlSQL(强大的ORM框架)、upload(本地文件上传和七牛云文件上传)、redis(缓存)、ehcache(缓存)、email(发送各种类型邮件)、task(基础定时任务)、quartz(动态管理定时任务)、xxl-job(分布式定时任务)、swagger(API接口管理测试)、security(基于RBAC的动态权限认证)、SpringSession(Session共享)、Zookeeper(结合AOP实现分布式锁)、RabbitMQ(消息队列)、Kafka(消息队列)、websocket(服务端推送监控服务器运行信息)、socket.io(聊天室)、ureport2(**式报表)、打包成war文件、集成 ElasticSearch(基本操作和高级查询)、Async(异步任务)、集成Dubbo(采用官方的starter)、MongoDB(文档数据库)、neo4j(图数据库)、docker(容器化)、JPA多数据源、Mybatis多数据源、代码生成器、GrayLog(日志收集)、JustAuth(第三方登录)、LDAP(增删改查)、动态添加/切换数据源、单机限流(AOP + Guava RateLimiter)、分布式限流(AOP + Redis + Lua)、ElasticSearch 7.x(使用官方 Rest High Level Client)、HTTPS。
profile page
Code for Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
Simple & fast Koa v2 Framework
A finanical management system based python
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
Unofficial PyTorch implementation of "Keyword Transformer: A Self-Attention Model for Keyword Spotting", Berg et al. 2021.
Collection of PyTorch implementations of Spoken Keyword Spotting presented in research papers.
Scene recognition tool based on pytorch. Provide training, test and deployment functions, as well as many pretrained models.
Model analyzer in PyTorch
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
Learning Efficient Representations for Keyword Spotting with Triplet Loss
Tutorial on PhD Application
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Unet based Kears and TensorFlow
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
An intelligent multimodal-learning based system for video, product and ads analysis. Based on the system, people can build a lot of downstream applications such as product recommendation, video retrieval, etc.