Convolutional Neural Network for Text Classification in Tensorflow
Simple Tensorflow implementation of StarGAN (CVPR 2018 Oral)
3D reconstruction with neural networks using Tensorflow
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
Pretrained models for TensorFlow.js
A Deep Learning Toolkit for Computer Vision
An open-source implementation of the AlphaGoZero algorithm
A general-purpose neural model for efficient learning of entity embeddings for solving a wide variety of problems
An implementation of Nvidia's fast photorealistic style transfer algorithm. Given a content photo and a style photo, the code can transfer the style of the style photo to the content photo.
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
Real-time object detection and classification
Keras implementation of RetinaNet object detection
Uniform Manifold Approximation and Projection
High-quality implementations of reinforcement learning algorithms
Image-to-image translation using conditional adversarial nets
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Code for Densely Connected Convolutional Networks (DenseNets)
Explaining the predictions of any machine learning classifier
Facebook AI Research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
A generic image detection program that uses Tensorflow and a pre-trained Inception CNN model
Keras implementation of Nested LSTMs
Neural Style Transfer For Chinese Characters
TensorFlow implementation for audio neural style
Feedforward style transfer
A method to generate speech across multiple speakers
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
Torch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
PyTorch implementation of Tacotron speech synthesis model.