tensorpack 0.8.3

Neural Network Toolbox on TensorFlow

.. figure:: .github/tensorpack.png
:alt: Tensorpack

Tensorpack
Tensorpack is a training interface based on TensorFlow.

|Build Status| |ReadTheDoc| |Gitter chat| |model-zoo|

Features:
---------

It's Yet Another TF wrapper, but different in:

1. Focus on **training speed**.

- Speed comes for free with tensorpack -- it uses TensorFlow in the
**efficient way** with no extra overhead. On different CNNs, it
runs `1.2~5x
faster <https://github.com/tensorpack/benchmarks/tree/master/other-wrappers>`__
than the equivalent Keras code.

- Data-parallel multi-GPU training is off-the-shelf to use. It
scales as well as Google's `official
benchmark <https://www.tensorflow.org/performance/benchmarks>`__.

- See
`tensorpack/benchmarks <https://github.com/tensorpack/benchmarks>`__
for the benchmark scripts.

2. Focus on **large datasets**.

- It's painful to read/preprocess data through TF. Tensorpack helps
you load large datasets (e.g. ImageNet) in **pure Python** with
autoparallelization.

3. It's not a model wrapper.

- There are too many symbolic function wrappers in the world.
Tensorpack includes only a few common models. But you can use any
symbolic function library inside tensorpack, including
tf.layers/Keras/slim/tflearn/tensorlayer/....

See
`tutorials <http://tensorpack.readthedocs.io/en/latest/tutorial/index.html>`__
to know more about these features.

`Examples <examples>`__:
------------------------

Instead of showing you 10 random networks with random accuracy,
`tensorpack examples <examples>`__ faithfully replicate papers and care
about performance. And everything runs on multiple GPUs. Some
highlights:

Vision:
~~~~~~~

- `Train ResNet <examples/ResNet>`__ and `other
models <examples/ImageNetModels>`__ on ImageNet.
- `Train Faster-RCNN / Mask-RCNN on COCO object
detection <examples/FasterRCNN>`__
- `Generative Adversarial Network(GAN) variants <examples/GAN>`__,
including DCGAN, InfoGAN, Conditional GAN, WGAN, BEGAN, DiscoGAN,
Image to Image, CycleGAN.
- `DoReFa-Net: train binary / low-bitwidth CNN on
ImageNet <examples/DoReFa-Net>`__
- `Fully-convolutional Network for Holistically-Nested Edge
Detection(HED) <examples/HED>`__
- `Spatial Transformer Networks on MNIST
addition <examples/SpatialTransformer>`__
- `Visualize CNN saliency maps <examples/Saliency>`__
- `Similarity learning on MNIST <examples/SimilarityLearning>`__

Reinforcement Learning:
~~~~~~~~~~~~~~~~~~~~~~~

- `Deep Q-Network(DQN) variants on Atari
games <examples/DeepQNetwork>`__, including DQN, DoubleDQN,
DuelingDQN.
- `Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI
Gym <examples/A3C-Gym>`__

Speech / NLP:
~~~~~~~~~~~~~

- `LSTM-CTC for speech recognition <examples/CTC-TIMIT>`__
- `char-rnn for fun <examples/Char-RNN>`__
- `LSTM language model on PennTreebank <examples/PennTreebank>`__

Install:
--------

Dependencies:

- Python 2.7 or 3
- Python bindings for OpenCV (Optional, but required by a lot of
features)
- TensorFlow >= 1.3.0 (Optional if you only want to use
``tensorpack.dataflow`` alone as a data processing library)

::

# install git, then:
pip install -U git+https://github.com/ppwwyyxx/tensorpack.git
# or add `--user` to avoid system-wide installation.

Citing Tensorpack:
------------------

If you use Tensorpack in your research or wish to refer to the examples,
please cite with:

::

@misc{wu2016tensorpack,
title={Tensorpack},
author={Wu, Yuxin and others},
howpublished={\url{https://github.com/tensorpack/}},
year={2016}
}

.. |Build Status| image:: https://travis-ci.org/ppwwyyxx/tensorpack.svg?branch=master
:target: https://travis-ci.org/ppwwyyxx/tensorpack
.. |ReadTheDoc| image:: https://readthedocs.org/projects/tensorpack/badge/?version=latest
:target: http://tensorpack.readthedocs.io/en/latest/index.html
.. |Gitter chat| image:: https://badges.gitter.im/gitterHQ/gitter.png
:target: https://gitter.im/tensorpack/users
.. |model-zoo| image:: https://img.shields.io/badge/model-zoo-brightgreen.svg
:target: http://models.tensorpack.com