Swift Tensorflow Starter
A Dockerized, Swift Package Manager enabled starter repository for Swift for TensorFlow projects.
System for synthesizing Java API idioms, powered by Neural Sketch Learning
A natural language data augmentation tool that helps developers create and expand domain specific chatbot training datasets for machine learning algorithms
An Extensive, Lightweight, and Flexible platform for game research. We have used it to build our Go playing bot, ELF OpenGo, which achieved a 14-0 record versus four global top-30 players in April 2018.
A Python toolbox designed to facilitate dimensionality reduction-based visual explorations of high-dimensional data to gain geometric insights
Compiler for Neural Network hardware accelerators
The source code of ‘Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network’
Deep 3DMM facial expression parameter extraction
Implementation of the Boundary Attack algorithm as described in “Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models.”
An implementation of “QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension” with PyTorch
Swift for TensorFlow gives you the power of TensorFlow directly integrated into the Swift programming language. With Swift, you can write the following imperative code, and Swift automatically turns it into a single TensorFlow Graph and runs it with the full performance of TensorFlow Sessions on CPU, GPU and TPU.
A PyTorch library for machine translation that provides training for sequence-to-sequence models
Like to add your project? tweet @stkim1!