Welcome.
unique-chan Goto Github PK
Name: Yechan Kim
Type: User
Company: GIST
Bio: GIST, Machine Learning and Vision Lab.
Location: Korea
Name: Yechan Kim
Type: User
Company: GIST
Bio: GIST, Machine Learning and Vision Lab.
Location: Korea
ποΈ LabelImg is a graphical image annotation tool and label object bounding boxes in images
TF 2 implementation Learning to Resize Images for Computer Vision Tasks (https://arxiv.org/abs/2103.09950v1).
PyTorch Implementation of Focal Loss and Lovasz-Softmax Loss
Datasets and Code for MaskCOV (accepted in Pattern Recognition)
According to YOLOv3 and SORT algorithms, counting multi-type vehicles. Implemented by Pytorch.
Official page of the Multi-weather city dataset.
The sample code for a large-scale crowd counting dataset, NWPU-Crowd.
Object Detection and Multi-Object Tracking
A PyTorch implementation of "Parameter-Free Loss for Class-Imbalanced Deep Learning in Image Classification"
Pedestrian-Counting (Under Construction!!!)
Pytorch implementation for CVPR 2017 "Joint Detection and Identification Feature Learning for Person Search"
Gradually-Warmup Learning Rate Scheduler for PyTorch
Minimal PyTorch implementation of YOLOv3
Implementation of Reinforcement Learning algorithms in Python, based on Sutton's & Barto's Book (Ed. 2)
Solutions of Reinforcement Learning, An Introduction
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
PyTorch implementation of the paper "Learning to Resize Images for Computer Vision Tasks" on Imagenette and Imagewoof datasets
Simple Image Classification Code (PyTorch)
Self-supervised Label Augmentation via Input Transformations (ICML 2020)
Unofficial Implementation for "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Model"
Image super resolution datasets for use with the super-image library.
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
π The TensorFlow Object Counting API is an open source framework built on top of TensorFlow and Keras that makes it easy to develop object counting systems!
μνΈνλ λμ€κ΅ν΅ κ΅ν΅μΉ΄λ λΉ λ°μ΄ν°μμμ κ΄κ΄κ° O-D ν΅νν¨ν΄ μΆμΆ μκ³ λ¦¬μ¦
Welcome.
AMD: ARMA3 military target detection on remote sensing imagery
Vehicle-Counting
This is he code maintaining platform for multi-view crowd counting.
The code of the Object Counting API, implemented with the YOLO algorithm and with the SORT algorithm
A declarative, efficient, and flexible JavaScript library for building user interfaces.
π 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. πππ
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 β€οΈ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.