Neural Network Toolbox on TensorFlow
Project description
.. figure:: .github/tensorpack.png
:alt: Tensorpack
Tensorpack
Tensorpack is a training interface based on TensorFlow.
|Build Status| |ReadTheDoc| |Gitter chat|
See some `examples <examples>`__ to learn about the framework.
Everything runs on multiple GPUs, because why not?
Vision:
~~~~~~~
- `Train ResNet/SE-ResNet on ImageNet <examples/ResNet>`__
- `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>`__
Examples are not only for demonstration of the framework -- you can
train them and reproduce the results in papers.
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
**correct way** with no extra overhead. On various CNNs, it runs
1.5~1.7x faster than the equivalent Keras code.
- Data-parallel multi-GPU training is off-the-shelf to use. It is as
fast as Google's `official
benchmark <https://www.tensorflow.org/performance/benchmarks>`__.
You cannot beat its speed unless you're a TensorFlow expert.
- See
`tensorpack/benchmarks <https://github.com/tensorpack/benchmarks>`__
for some 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 already too many symbolic function wrappers. Tensorpack
includes only a few common models, but you can use any other
wrappers within tensorpack, including
sonnet/Keras/slim/tflearn/tensorlayer/....
See
`tutorials <http://tensorpack.readthedocs.io/en/latest/tutorial/index.html>`__
to know more about these features.
Install:
--------
Dependencies:
- Python 2.7 or 3
- Python bindings for OpenCV (Optional, but required by a lot of
features)
- TensorFlow >= 1.2.0 (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.
.. |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
:alt: Tensorpack
Tensorpack
Tensorpack is a training interface based on TensorFlow.
|Build Status| |ReadTheDoc| |Gitter chat|
See some `examples <examples>`__ to learn about the framework.
Everything runs on multiple GPUs, because why not?
Vision:
~~~~~~~
- `Train ResNet/SE-ResNet on ImageNet <examples/ResNet>`__
- `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>`__
Examples are not only for demonstration of the framework -- you can
train them and reproduce the results in papers.
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
**correct way** with no extra overhead. On various CNNs, it runs
1.5~1.7x faster than the equivalent Keras code.
- Data-parallel multi-GPU training is off-the-shelf to use. It is as
fast as Google's `official
benchmark <https://www.tensorflow.org/performance/benchmarks>`__.
You cannot beat its speed unless you're a TensorFlow expert.
- See
`tensorpack/benchmarks <https://github.com/tensorpack/benchmarks>`__
for some 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 already too many symbolic function wrappers. Tensorpack
includes only a few common models, but you can use any other
wrappers within tensorpack, including
sonnet/Keras/slim/tflearn/tensorlayer/....
See
`tutorials <http://tensorpack.readthedocs.io/en/latest/tutorial/index.html>`__
to know more about these features.
Install:
--------
Dependencies:
- Python 2.7 or 3
- Python bindings for OpenCV (Optional, but required by a lot of
features)
- TensorFlow >= 1.2.0 (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.
.. |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
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tensorpack-0.8.1.tar.gz
(165.6 kB
view hashes)
Built Distribution
tensorpack-0.8.1-py2.py3-none-any.whl
(233.0 kB
view hashes)
Close
Hashes for tensorpack-0.8.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b575e24632d22f2c2dbd369e1cf139a535ac085da37e900e6b448598c7bb3272 |
|
MD5 | eaaa7d43d943531b2374254771570ed4 |
|
BLAKE2b-256 | b641dcd44ed8c32e2f5e870f2e416c23710fb4d0fc215b4c364feb051485ee61 |