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

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)