TensorFlow Models

This repository contains machine learning models implemented in TensorFlow. The models are maintained by their respective authors.

To propose a model for inclusion please submit a pull request.

Models

autoencoder -- various autoencoders
inception -- deep convolutional networks for computer vision
namignizer -- recognize and generate names
neural_gpu -- highly parallel neural computer
privacy -- privacy-preserving student models from multiple teachers
resnet -- deep and wide residual networks
slim -- image classification models in TF-Slim
swivel -- the Swivel algorithm for generating word embeddings
syntaxnet -- neural models of natural language syntax
textsum -- sequence-to-sequence with attention model for text summarization.
transformer -- spatial transformer network, which allows the spatial manipulation of data within the network
im2txt -- image-to-text neural network for image captioning.

Implementation of the Neural Programmer model described in https://openreview.net/pdf?id=ry2YOrcge

Download the data from http://www-nlp.stanford.edu/software/sempre/wikitable/ Change the data_dir FLAG to the location of the data

Training: python neural_programmer.py

The models are written to FLAGS.output_dir

Testing: python neural_programmer.py --evaluator_job=True

The models are loaded from FLAGS.output_dir. The evaluation is done on development data.

Maintained by Arvind Neelakantan (arvind2505)