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.

Quoc Le b905b41285 add a readme vor 9 Jahren
.github dc7791d01c Create ISSUE_TEMPLATE.md (#124) vor 10 Jahren
autoencoder a472ac9525 merged changes from #25 vor 10 Jahren
compression b181b9885c Update README with results for comparison. vor 9 Jahren
differential_privacy a66b9e13c9 added semi-supervised training of the student using improved-gan (#655) vor 9 Jahren
im2txt 0cba7a4b5d Remove comment that TensorFlow must be built from source. vor 9 Jahren
inception bf51d43420 fix module object has no attribute NodeDef for tensorflow 0.11 (#572) vor 9 Jahren
lm_1b fdc4ce37a4 Fix README vor 9 Jahren
namignizer 76f567df5f add the namignizer model (#147) vor 10 Jahren
neural_gpu a803bf4171 Add to neural_gpu documentation. vor 9 Jahren
neural_programmer b905b41285 add a readme vor 9 Jahren
resnet d93ffd0b69 Allow softplacement for ResNet vor 9 Jahren
slim ea207d8a4d Updating README.md vor 9 Jahren
street f42469ef90 Updated download instructions to match reality vor 9 Jahren
swivel f3144eb061 Add sys.stdout.flush() vor 9 Jahren
syntaxnet 5eff490de4 Fix POS tagging score of Ling et al.(2005) vor 9 Jahren
textsum 5e875226bc Explicitly set state_is_tuple=False. vor 9 Jahren
transformer d816971032 Use tf.softmax_cross_entropy_with_logits to calculate loss (#181) vor 9 Jahren
video_prediction d67ea24901 video prediction model code vor 9 Jahren
.gitignore 3e6caf5ff0 Add a .gitignore file. (#164) vor 10 Jahren
.gitmodules 32ab5a58dd Adding SyntaxNet to tensorflow/models (#63) vor 10 Jahren
AUTHORS 41c52d60fe Spatial Transformer model vor 10 Jahren
CONTRIBUTING.md d84df16bc3 fixed contribution guidelines vor 10 Jahren
LICENSE 7c41e653dc Update LICENSE vor 10 Jahren
README.md 3581d5f244 My message vor 9 Jahren
WORKSPACE ac0829fa2b Consolidate privacy/ and differential_privacy/. vor 9 Jahren

README.md

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)