ap229997

redner

Differentiable rendering without approximation.

EmbodiedQA

Train embodied agents that can answer questions in environments

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

pixel_rnn

Working Theano implementation of Pixel RNN on MNIST.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

SQuAD-explorer

Visually Explore the Stanford Question Answering Dataset

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

GraphRNN

Pixel2Mesh

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.

BERT-pytorch

Google AI 2018 BERT pytorch implementation

Wave-U-Net

Implementation of the Wave-U-Net for audio source separation

DeepMimic

Motion imitation with deep reinforcement learning.

NQG

Code for the paper "Neural Question Generation from Text: A Preliminary Study"

adv_attack_capsnet

Tensorflow Implementation of Adversarial Attack to Capsule Networks

self-attention-gan

WAGE.pytorch

Reproduction of WAGE in PyTorch.

scale-time-lattice

Code for our CVPR 2018 paper "Optimizing Video Object Detection via a Scale-Time Lattice".

swagaf

Repository for paper "SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference"

Reinforcement-Learning

Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning

convnet-aig

PyTorch implementation for Convolutional Networks with Adaptive Inference Graphs

defensegan

Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)

DANet

Dual Attention Network for Scene Segmentation (CVPR2019)

DiscoGAN

Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

graph-rcnn.pytorch

[ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"

rrnet

basic rrnet implementation

dopamine

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

neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer

msg-gan-v1

MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)

piqa

Phrase-Indexed Question Answering (PIQA)

BicycleGAN

Toward Multimodal Image-to-Image Translation