- Seoul, Republic of Korea
- https://gunhochoi.simplybook.asia/v2/
Stars
A Chrome extension that adds a 3d photo effect to instagram pages.
Transformer-based image captioning extension for pytorch/fairseq
Facebook AI Research's Automatic Speech Recognition Toolkit
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
3d plotting for Python in the Jupyter notebook based on IPython widgets using WebGL
ProGAN with Standard, WGAN, WGAN-GP, LSGAN, BEGAN, DRAGAN, Conditional GAN, InfoGAN, and Auxiliary Classifier GAN training methods
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Introduction to Deep Reinforcement Learning
Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (https://arxiv.org/pdf/1807.03247.pdf)
Start Tensorboard in Jupyter Notebook
Unofficial PyTorch implementation of the paper titled "Progressive growing of GANs for improved Quality, Stability, and Variation"
Differentiable architecture search for convolutional and recurrent networks
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Example code for the book Fluent Python, 1st Edition (O'Reilly, 2015)
Summary (in Korean) and python implementation of 'Reinforcement Learning: An Introduction' written by Sutton & Barto
Model summary in PyTorch similar to `model.summary()` in Keras
Image augmentation library in Python for machine learning.
Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr
A small package to create visualizations of PyTorch execution graphs
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Deep Learning Papers on Medical Image Analysis
Style transfer, deep learning, feature transform