This package is for reproduction of anytime neural networks and Log-DenseNet.

An example of Log-DenseNet. An example of anytime network work

The following is the original README of the package tensorpack, which this work is based on.

Tensorpack is a training interface based on TensorFlow.

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 training 1.2~5x faster 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.

   • Distributed data-parallel training is also supported and scales well. See tensorpack/benchmarks for more benchmark scripts.

2. Focus on large datasets.

   • It's unnecessary to read/preprocess data with a new language called 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 to know more about these features.

Examples:

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

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
• 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}
}