The fastai book, published as Jupyter Notebooks

A collection of various deep learning architectures, models, and tips

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Toturials coming with the "data science roadmap" picture.

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Scenarios, tutorials and demos for Autonomous Driving

Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+

subpixel: A subpixel convnet for super resolution with Tensorflow

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning mode…

Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)

LSTM trained on the first five ASOIAF/GOT books

Object Detection

A facial expression classification system that recognizes 6 basic emotions: happy, sad, surprise, fear, anger and neutral.

TensorFlow implementation for audio neural style.

semantic similarity framework for knowledge graph

Visual Question Answering Demo on pretrained model

Weakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).

Image completion using deep convolutional generative adversarial nets in tensorflow

Code for "A-NICE-MC: Adversarial Training for MCMC"

knowledge-graph datasets