A Deep Reinforcement Learning Library for Automated Trading in Quantitative Finance.

An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.

A simple Blockchain in Python

UniLM - Unified Language Model Pre-training

A cryptocurrency trading environment using deep reinforcement learning and OpenAI's gym

A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.

FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension

Subword Language Model for Query Auto-Completion

Useful extra functionality for TensorFlow 2.0 maintained by SIG-addons

Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743

BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer

Global-Locally Self-Attentive Dialogue State Tracker

Ordered Neurons LSTM

An Open Source Machine Learning Framework for Everyone

Implementation of Segnet, FCN, UNet and other models in Keras.

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

tf.keras + tf.data with Eager Execution

This is a drop-in Keras layer for ELMo embeddings.

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

A library for efficient similarity search and clustering of dense vectors.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Connecting Torch to StarCraft

Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

Official Tensorflow implementation of drl-RPN: Deep Reinforcement Learning of Region Proposal Networks (CVPR 2018 paper)