NeuralDialog-CVAE - Tensorflow Implementation of Knowledge-Guided CVAE for dialog generation

  •        31

We provide a TensorFlow implementation of the CVAE-based dialog model described in Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders, published as a long paper in ACL 2017. See the paper for more details. The outputs will be printed to stdout and generated responses will be saved at test.txt in the test_path.



Related Projects

cakechat - CakeChat: Emotional Generative Dialog System

  •    Python

It is written in Theano and Lasagne. It uses end-to-end trained embeddings of 5 different emotions to generate responses conditioned by a given emotion. The code is flexible and allows to condition a response by an arbitrary categorical variable defined for some samples in the training data. With CakeChat you can, for example, train your own persona-based neural conversational model[5] or create an emotional chatting machine without external memory[4].

cppn-gan-vae-tensorflow - Train CPPNs as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images

  •    Python

Train Compositional Pattern Producing Network as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images. Run python from the command line to train from scratch and experiment with different settings.

autoencoding_beyond_pixels - Generative image model with learned similarity measures

  •    Python

Implementation of the method described in our Arxiv paper. We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. Moreover, we show that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.

Pyro - Deep universal probabilistic programming with Python and PyTorch

  •    Python

Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling.

DeepJ - A deep learning model for style-specific music generation.

  •    Python

Recent advances in deep neural networks have enabled algorithms to compose music that is comparable to music composed by humans. However, few algorithms allow the user to generate music with tunable parameters. The ability to tune properties of generated music will yield more practical benefits for aiding artists, filmmakers, and composers in their creative tasks. In this paper, we introduce DeepJ - an end-to-end generative model that is capable of composing music conditioned on a specific mixture of composer styles. Our innovations include methods to learn musical style and music dynamics. We use our model to demonstrate a simple technique for controlling the style of generated music as a proof of concept. Evaluation of our model using human raters shows that we have improved over the Biaxial LSTM approach. Clone Python MIDI ( cd python-midi then install using python3 install.

TC-Bot - User Simulation for Task-Completion Dialogues

  •    OpenEdge

An implementation of the End-to-End Task-Completion Neural Dialogue Systems and A User Simulator for Task-Completion Dialogues. This document describes how to run the simulation and different dialogue agents (rule-based, command line, reinforcement learning). More instructions to plug in your customized agents or user simulators are in the Recipe section of the paper.



VIBES stands for Variational Inference in BayES Nets. It consists of a graphical Bayes Net editor and an inference engine which allows variational inference to be applied automatically using Variational Message Passing.

tvm - bring deep learning workloads to bare metal

  •    C++

TVM is a Tensor intermediate representation(IR) stack for deep learning systems. It is designed to close the gap between the productivity-focused deep learning frameworks, and the performance- and efficiency-focused hardware backends. TVM works with deep learning frameworks to provide end to end compilation to different backends. Checkout our announcement for more details.© Contributors, 2017. Licensed under an Apache-2.0 license.

NeuronBlocks - NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego

  •    Python

NeuronBlocks is a NLP deep learning modeling toolkit that helps engineers/researchers to build end-to-end pipelines for neural network model training for NLP tasks. The main goal of this toolkit is to minimize developing cost for NLP deep neural network model building, including both training and inference stages. NeuronBlocks consists of two major components: Block Zoo and Model Zoo.

pix2code - pix2code: Generating Code from a Graphical User Interface Screenshot

  •    Python

Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications. In this paper, we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies). The following software is shared for educational purposes only. The author and its affiliated institution are not responsible in any manner whatsoever for any damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of the use or inability to use this software.

espnet - End-to-End Speech Processing Toolkit

  •    Shell

ESPnet is an end-to-end speech processing toolkit, mainly focuses on end-to-end speech recognition, and end-to-end text-to-speech. ESPnet uses chainer and pytorch as a main deep learning engine, and also follows Kaldi style data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. To use cuda (and cudnn), make sure to set paths in your .bashrc or .bash_profile appropriately.

DeepQA - My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

  •    Python

This work tries to reproduce the results of A Neural Conversational Model (aka the Google chatbot). It uses a RNN (seq2seq model) for sentence predictions. It is done using python and TensorFlow. The loading corpus part of the program is inspired by the Torch neuralconvo from macournoyer.

awesome-scalability - Scalable, Available, Stable, Performant, and Intelligent System Design Patterns


An updated and curated list of readings to illustrate best practices and patterns in building scalable, available, stable, performant, and intelligent large-scale systems. Concepts are explained in the articles of prominent engineers and credible references. Case studies are taken from battle-tested systems that serve millions to billions of users. Understand your problems: scalability problem (fast for a single user but slow under heavy load) or performance problem (slow for a single user) by reviewing some design principles and checking how scalability and performance problems are solved at tech companies. The section of intelligence are created for those who work with data and machine learning at big (data) and deep (learning) scale.

RLSeq2Seq - Deep Reinforcement Learning For Sequence to Sequence Models

  •    Python

NOTE: THE CODE IS UNDER DEVELOPMENT, PLEASE ALWAYS PULL THE LATEST VERSION FROM HERE. In recent years, sequence-to-sequence (seq2seq) models are used in a variety of tasks from machine translation, headline generation, text summarization, speech to text, to image caption generation. The underlying framework of all these models are usually a deep neural network which contains an encoder and decoder. The encoder processes the input data and a decoder receives the output of the encoder and generates the final output. Although simply using an encoder/decoder model would, most of the time, produce better result than traditional methods on the above-mentioned tasks, researchers proposed additional improvements over these sequence to sequence models, like using an attention-based model over the input, pointer-generation models, and self-attention models. However, all these seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently a completely fresh point of view emerged in solving these two problems in seq2seq models by using methods in Reinforcement Learning (RL). In these new researches, we try to look at the seq2seq problems from the RL point of view and we try to come up with a formulation that could combine the power of RL methods in decision-making and sequence to sequence models in remembering long memories. In this paper, we will summarize some of the most recent frameworks that combines concepts from RL world to the deep neural network area and explain how these two areas could benefit from each other in solving complex seq2seq tasks. In the end, we will provide insights on some of the problems of the current existing models and how we can improve them with better RL models. We also provide the source code for implementing most of the models that will be discussed in this paper on the complex task of abstractive text summarization.

keras-molecules - Autoencoder network for learning a continuous representation of molecular structures

  •    Python

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This generative model allows efficient search and optimization through open-ended spaces of chemical compounds. We train deep neural networks on hundreds of thousands of existing chemical structures to construct two coupled functions: an encoder and a decoder. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to the discrete representation from this latent space.

delta - DELTA is a deep learning based natural language and speech processing platform.

  •    Python

DELTA is a deep learning based end-to-end natural language and speech processing platform. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. DELTA is mainly implemented using TensorFlow and Python 3. For details of DELTA, please refer to this paper.

jetson-reinforcement - Deep reinforcement learning GPU libraries for NVIDIA Jetson with PyTorch, OpenAI Gym, and Gazebo robotics simulator

  •    C++

In this tutorial, we'll be creating artificially intelligent agents that learn from interacting with their environment, gathering experience, and a system of rewards with deep reinforcement learning (deep RL). Using end-to-end neural networks that translate raw pixels into actions, RL-trained agents are capable of exhibiting intuitive behaviors and performing complex tasks. Ultimately, our aim will be to train reinforcement learning agents from virtual robotic simulation in 3D and transfer the agent to a real-world robot. Reinforcement learners choose the best action for the agent to perform based on environmental state (like camera inputs) and rewards that provide feedback to the agent about it's performance. Reinforcement learning can learn to behave optimally in it's environment given a policy, or task - like obtaining the reward.