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 f7ee285d9b move to a new place 9 lat temu
.github dc7791d01c Create ISSUE_TEMPLATE.md (#124) 10 lat temu
autoencoder a472ac9525 merged changes from #25 10 lat temu
compression b181b9885c Update README with results for comparison. 9 lat temu
differential_privacy a66b9e13c9 added semi-supervised training of the student using improved-gan (#655) 9 lat temu
im2txt 0cba7a4b5d Remove comment that TensorFlow must be built from source. 9 lat temu
inception bf51d43420 fix module object has no attribute NodeDef for tensorflow 0.11 (#572) 10 lat temu
lm_1b fdc4ce37a4 Fix README 10 lat temu
namignizer 76f567df5f add the namignizer model (#147) 10 lat temu
neural_gpu a803bf4171 Add to neural_gpu documentation. 10 lat temu
neural_programmer f7ee285d9b move to a new place 9 lat temu
resnet d93ffd0b69 Allow softplacement for ResNet 10 lat temu
slim ea207d8a4d Updating README.md 9 lat temu
street f42469ef90 Updated download instructions to match reality 10 lat temu
swivel f3144eb061 Add sys.stdout.flush() 10 lat temu
syntaxnet 5eff490de4 Fix POS tagging score of Ling et al.(2005) 10 lat temu
textsum 5e875226bc Explicitly set state_is_tuple=False. 10 lat temu
transformer d816971032 Use tf.softmax_cross_entropy_with_logits to calculate loss (#181) 10 lat temu
video_prediction d67ea24901 video prediction model code 10 lat temu
.gitignore 3e6caf5ff0 Add a .gitignore file. (#164) 10 lat temu
.gitmodules 32ab5a58dd Adding SyntaxNet to tensorflow/models (#63) 10 lat temu
AUTHORS 41c52d60fe Spatial Transformer model 10 lat temu
CONTRIBUTING.md d84df16bc3 fixed contribution guidelines 10 lat temu
LICENSE 7c41e653dc Update LICENSE 10 lat temu
README.md 3581d5f244 My message 9 lat temu
WORKSPACE ac0829fa2b Consolidate privacy/ and differential_privacy/. 10 lat temu

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)