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

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)