tanzeyy
Interested in programming, reinforcement learning, distributed computation and data systems.
Beijing
Pinned Repositories
DOLG-instance-retrieval
Official Implementation of DOLG (ICCV 2021)
fate_demo
js4py
JavaScript tutorial for Python programmers,Python程序员的JavaScript教程。
Learn-to-Pythonic
Notes in python learning.
Prioritized_n-step_DoubleDQN
PyTorch implementation of prioritized n-step double DQN
raspberrypi_robot
reinforcement_learning
Code for learning Reinforcement Learning: An Introduction
tanzeyy's Repositories
tanzeyy/DOLG-instance-retrieval
Official Implementation of DOLG (ICCV 2021)
tanzeyy/js4py
JavaScript tutorial for Python programmers,Python程序员的JavaScript教程。
tanzeyy/fate_demo
tanzeyy/Prioritized_n-step_DoubleDQN
PyTorch implementation of prioritized n-step double DQN
tanzeyy/reinforcement_learning
Code for learning Reinforcement Learning: An Introduction
tanzeyy/arrow
Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing
tanzeyy/bvt-backend
tanzeyy/glaucus
A general data-flow-based machine learning suit combining auto machine learning and multiple simplified machine learning algorithm for unprofessional data scenitists
tanzeyy/bvt-web
tanzeyy/chatgpt_system_prompt
store all agent's system prompt
tanzeyy/DDPG
DDPG implementation using PyTorch
tanzeyy/dockerfiles
Dockerfiles for developing.
tanzeyy/geektime-rust
我的极客时间 Rust 课程的代码仓库,随课程更新
tanzeyy/gitignore
A collection of useful .gitignore templates
tanzeyy/homework
Assignments for CS294-112.
tanzeyy/HyperLPR
基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.
tanzeyy/L2RPN
CodaLab L2RPN: Learning to Run a Power Network
tanzeyy/Megatron-LM
Ongoing research training transformer models at scale
tanzeyy/metaflow
:rocket: Build and manage real-life data science projects with ease!
tanzeyy/MultiFormatterVSCode
It's a Visual Studio Code that allows you to use multiple formatters in just one run
tanzeyy/Pai-Megatron-Patch
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
tanzeyy/PARL
A high-performance distributed training framework for Reinforcement Learning
tanzeyy/pyfilesystem2
Python's Filesystem abstraction layer
tanzeyy/python_backend
Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.
tanzeyy/Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
tanzeyy/research-proposal-template
LaTeX template to outline and draft academic papers (or theses) in Computer Science (in English and German language)
tanzeyy/revisitop
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
tanzeyy/SpA-GAN_for_cloud_removal
This is the source code of my graduation thesis named Cloud Removal for High-resolution Remote Sensing Imagery based on Generative Adversarial Networks. In this work, I proposed a novel model called spatial attention generative adversarial networks or SpA GAN, which use spatial attention networks (SPANet) as generator.
tanzeyy/tonic
A native gRPC client & server implementation with async/await support.
tanzeyy/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators