Flickr-Faces-HQ (FFHQ) is a high-quality image dataset of human faces.
BERT, published by Google, is new way to obtain pre-trained language model word representation. Many NLP tasks are benefit from BERT to get the SOTA.
This code helps you classify digits using openCV and Convolutional Neural Network.
This is an implementation of "UNet++: A Nested U-Net Architecture for Medical Image Segmentation" in Keras deep learning framework (Tensorflow as backend).
You feed it your Python app, it does a lot of clever things, and spits out an executable or extension module.
A simple project that demonstrates how to create an executable from a Python project.
Created in April 2017, unCaptcha achieved 85% accuracy defeating Google's ReCaptcha.
This repository contains PyTorch implementations of deep reinforcement learning algorithms.
ASCII snow in your terminal.
A Tensorflow Implementation of R-net: Machine reading comprehension with self matching networks.
This repository contains the dataset of natural images of grocery items.
In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results.
This is alternative implementation of "Synchronized Multi-GPU Batch Normalization" which computes global stats across gpus instead of locally computed.
Dynamic web based reports/dashboards in Python.
Connect(); 2018 - AI Visual Provision Sample App.
This is a Pytorch implementation of CFUN for whole heart segmentation.
ggnewscale tries to make it painless to use multiple color and fill scales in ggplot2. It’s very experimental, so use at your own risk!
Training and evalutation code for the paper Finding beans in burgers: Deep semantic-visual embedding with localization.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
Neuroevolution-Bots is a personal project that demonstrates neuroevolution in a browser environment using TensorFlow.js
PyOD is a comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data.
We present Visual Object Networks (VON), an end-to-end adversarial learning framework that jointly models 3D shapes and 2D images.
Loguru is a library which aims to bring enjoyable logging in Python.
JAX is Autograd and XLA, brought together for high-performance machine learning research.
Pytorch-based tools for visualizing and understanding the neurons of a GAN