shenzhangzhou/tensorpack

Tensorpack is a training interface based on TensorFlow.

Features:

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

Focus on training speed.
- Speed comes for free with tensorpack -- it uses TensorFlow in the efficient 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 runs as fast as Google's official benchmark.
- See tensorpack/benchmarks for the benchmark scripts.
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.
It's not a model wrapper.
- There are too many symbolic function wrappers. Tensorpack includes only a few common models. You can use any symbolic function library inside tensorpack, including tflayers/Keras/slim/tflearn/tensorlayer/....

See tutorials to know more about these features.

Examples:

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

Vision:

Train ResNet 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:

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}
}

shenzhangzhou / tensorpack