katsura-jp Goto Github PK
Name: Naoki Katsura
Type: User
Company: Mercari, inc.
Bio: Software Engineer
Twitter: katsura_jp
Location: Tokyo, Japan
Name: Naoki Katsura
Type: User
Company: Mercari, inc.
Bio: Software Engineer
Twitter: katsura_jp
Location: Tokyo, Japan
fast image augmentation library and easy to use wrapper around other libraries
第23回PRMUアルゴリズムコンテスト用レポジトリ
Simultaneous object detection and tracking using center points.
Object Detection Metrics for COCO format
Video embeddings for retrieval - code for the paper "Use What You Have: Video retrieval using representations from collaborative experts"
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511
[CVPR2019] Dual Encoding for Zero-Example Video Retrieval
PyTorch implementation of "EfficientNet", ICML 2019
useful parts for experiment
Extract video feature from C3D pretrained on Sports-1M and Kinetics
A faster pytorch implementation of faster r-cnn
A PyTorch implementation of "Communication-Efficient Learning of Deep Networks from Decentralized Data", AISTATS, 2017
なろう小説風のタイトルをTransformerによって生成
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
主専攻実験(秋) 強化学習
勉強用
Open Source Computer Vision Library
LinearCyclicalLR scheduler implemented by Pytorch
Minimal PyTorch implementation of YOLOv3
PyTorch implementation of Gaussian YOLOv3 (including training code for COCO dataset)
TensorFlow implementation of "Simple Baselines for Human Pose Estimation and Tracking", ECCV 2018
example of albumentations
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond
Datasets, Transforms and Models specific to Computer Vision
Code and Experiments for ACL-IJCNLP 2021 Paper "Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering."
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.