Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Uniform Manifold Approximation and Projection
Phrase-Based & Neural Unsupervised Machine Translation
Tensorflow implementations of Relational Networks and a VQA dataset named Sort-of-CLEVR proposed by DeepMind.
A normalization technique that is able to learn different normalization operations for different normalization layers in a deep neural network in an end-to-end manner.
Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking
A MXNet implementation of Mask R-CNN
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Differentiable architecture search for convolutional and recurrent networks
Keras implementations of Generative Adversarial Networks.
Collection of generative models in Pytorch version
Collection of generative models in Tensorflow
Tensorflow implementation of a Neural Turing Machine
Signal prediction with a seq2seq RNN model in TensorFlow
TensorFlow implementation of ENet, trained on the Cityscapes dataset.
High-quality implementations of reinforcement learning algorithms
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
ShuffleNet implementation in TensorFlow
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error < 0.4%.
A TensorFlow implementation of Baidu's DeepSpeech architecture
Explaining the predictions of any machine learning classifier
Resources and Implementations of Generative Adversarial Nets which are focusing on how to stabilize training process and generate high quality images: DCGAN, WGAN, EBGAN, BEGAN, etc.
A PaddlePaddle implementation of DeepSpeech2 architecture for ASR.
A tensorflow implemention of EAST text detector
GloVe model for distributed word representation
Sentence embeddings (InferSent) and training code for NLI.
A Structured Self-attentive Sentence Embedding
PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM
A TensorFlow Implementation of the Transformer: Attention Is All You Need