happyxuwork/tensorpack

A Neural Net Training Interface on TensorFlow

Tensorpack is a neural network training interface based on TensorFlow.

Features:

It's Yet Another TF high-level API, with speed, readability and flexibility built together.

1. Focus on training speed.

   • Speed comes for free with Tensorpack -- it uses TensorFlow in the efficient way with no extra overhead. On common CNNs, it runs training 1.2~5x faster than the equivalent Keras code.

   • Data-parallel multi-GPU/distributed training strategy is off-the-shelf to use. It scales as well as Google's official benchmark.

   • See tensorpack/benchmarks for some benchmark scripts.

2. Focus on large datasets.

   • You don't usually need tf.data. Symbolic programming often makes data processing harder. Tensorpack helps you efficiently process 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 to know more about these features.

Examples:

We refuse toy examples. Instead of showing you 10 arbitrary networks trained on toy datasets, Tensorpack examples faithfully replicate papers and care about reproducing numbers, demonstrating its flexibility for actual research.

Vision:

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

Reinforcement Learning:

• Deep Q-Network(DQN) variants on Atari games, including DQN, DoubleDQN, DuelingDQN.
• Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym

Speech / NLP:

• LSTM-CTC for speech recognition
• char-rnn for fun
• LSTM language model on PennTreebank

Install:

Dependencies:

• Python 2.7 or 3.3+. Python 2.7 is supported until it retires in 2020.
• Python bindings for OpenCV (Optional, but required by a lot of features)
• TensorFlow >= 1.3. (If you only want to use tensorpack.dataflow alone as a data processing library, TensorFlow is not needed)

pip install --upgrade git+https://github.com/tensorpack/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}
}