Tensorflow Official Models

MM 05/24/2018

The files include:

-benchmark/

-boosted_trees/

-mnist/

-recommendataion/

-resnet/

-transformer/

-utils/

-wide_deep/

-.gitignore, -Dockerfile.cpu, -Dockerfile.gpu, -README.md, __init__.py, -requirements.txt

README.md

The TensorFlow official models are a collection of example models that use TensorFlow's high-level APIs. They are intended to be well-maintained, tested, and kept up to date with the latest TensorFlow API.

They should also be reasonably optimized for fast performance while still being easy to read.

The master branch of the models are in development, and they target the nightly binaries built from the master branch of Tenssorflow [1] .

We aim to keep them backwards compatible with the latest release when possible (currently TensorFlow 1.5), but we cannot always guarantee compatibility.

Stable versions of the official models targeting releases of TensorFlow are available as tagged branches or downloadable release [2] . Model repository version numbers match the target TensorFlow release, such that branch r1.4.0 [3] and release v1.4.0 [4] and are compatible with Tensorflw v1.4.0 [5].

If you are on a version of TensorFlow earlier than 1.4, please update your installation [6].

Below is a list of the models available:

boosted_trees [7]: A Gradient Boosted Trees model to classify higgs boson process from HIGGS Data Set.

mnist [8]: A basic model to classify digits from the MNIST dataset.

resnet [9]: A deep residual network that can be used to classify both CIFAR-10 and ImageNet's dataset of 1000 classes.

wide_deep[10]: A model that combines a wide model and deep network to classify census income data.

Running the models

The_Official Models _are made available as a Python module.

To run the models and associated scripts, add the top-level_/models _folder to the Python path with the command:export PYTHONPATH="$PYTHONPATH:/path/to/models"

To install dependencies pass-r official/requirements.txtto pip. (i.e.pip3 install --user -r official/requirements.txt)

To make Official Models easier to use, we are planning to create a pip installable Official Models package. This is being tracked in#917.

[0]

https://github.com/tensorflow/models/tree/master/official

[1]

https://github.com/tensorflow/tensorflow/tree/master

[2]

https://github.com/tensorflow/models/releases

[3]

https://github.com/tensorflow/models/tree/r1.4.0

[4]

https://github.com/tensorflow/models/releases/tag/v1.4.0