The fastai deep learning library, plus lessons and tutorials

fastai The fastai library simplifies training fast and accurate neural nets using modern best practices. See the fastai website to get started. The library is based on research into deep learning best practices undertaken

Related Repos



AKSHAYUBHAT Computational Healthcare Library The goal of Computational Healthcare Library is to help computer scientists perform high impact healthcare research by providing a simple interface to large publicly available healthcare datasets.
 

hzy46 fast-neural-style-tensorflow A tensorflow implementation for Perceptual Losses for Real-Time Style Transfer and Super-Resolution. This code is based on Tensorflow-Slim and OlavHN/fast-neural-style. Samples:
 

OpenNMT Im2Text A deep learning-based approach to learning the image-to-text conversion, built on top of the OpenNMT system. It is completely data-driven, hence can be used for a variety of image-to-text problems, such as image captionin
 

rupeshs Neural Song Style Transferring the style from one song onto another using artificial intelligence. This is based on the implementation neural-style-audio by Dmitry and Vadim. Options --content ,Content audio path
 

CYHSM Update on Alpha Zero All reanalysis of the Alpha Zero vs. Stockfish games can now be found here The -What The Hell- Moment When looking at specific chess games from grandmasters there sometimes comes a point in th
 

ProbabilisticNumerics SGD with Coupled Adaptive Batch Size (CABS) This is a TensorFlow implementation of SGD with Coupled Adaptive Batch Size (CABS). The Algorithm in a Nutshell CABS is an algorithm to dynamically adapt the batch size when
 

fferroni PhasedLSTM-Keras Keras implementation of Phased LSTM [https://arxiv.org/abs/1610.09513], from NIPS 2016. To install run: `pip install phased_lstm_keras` Works both with Theano and Tensorflow backend (tested on Theano 0.9 and Te
 

marekrei Sequence labeler This is a neural network sequence labeling system. Given a sequence of tokens, it will learn to assign labels to each token. Can be used for named entity recognition, POS-tagging, error detection, chunking, CCG s