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.
|
|
9 years ago | |
|---|---|---|
| .github | 9 years ago | |
| autoencoder | 9 years ago | |
| compression | 9 years ago | |
| differential_privacy | 9 years ago | |
| im2txt | 9 years ago | |
| inception | 9 years ago | |
| lm_1b | 9 years ago | |
| namignizer | 9 years ago | |
| neural_gpu | 9 years ago | |
| neural_programmer | 9 years ago | |
| resnet | 9 years ago | |
| slim | 9 years ago | |
| street | 9 years ago | |
| swivel | 9 years ago | |
| syntaxnet | 9 years ago | |
| textsum | 9 years ago | |
| transformer | 9 years ago | |
| video_prediction | 9 years ago | |
| .gitignore | 9 years ago | |
| .gitmodules | 9 years ago | |
| AUTHORS | 9 years ago | |
| CONTRIBUTING.md | 9 years ago | |
| LICENSE | 9 years ago | |
| README.md | 9 years ago | |
| WORKSPACE | 9 years ago |
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)