YiLiangNie/tensorpack

Neural Network Toolbox on TensorFlow

tensorpack

Neural Network Toolbox on TensorFlow

See some examples to learn about the framework:

Vision:

• DoReFa-Net: train binary / low-bitwidth CNN on ImageNet
• Train ResNet on ImageNet / Cifar10 / SVHN
• InceptionV3 on ImageNet
• Fully-convolutional Network for Holistically-Nested Edge Detection(HED)
• Spatial Transformer Networks on MNIST addition
• Visualize Saliency Maps by Guided ReLU
• 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

Unsupervised Learning:

• Generative Adversarial Network(GAN) variants, including DCGAN, InfoGAN, Conditional GAN, WGAN, DiscoGAN, Image to Image.

Speech / NLP:

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

The examples are not only for demonstration of the framework -- you can train them and reproduce the results in papers.

Features:

Describe your training task with three components:

1. DataFlow. process data in Python, with ease and speed.

   • Allows you to process data in Python without blocking the training, by multiprocess prefetch & TF Queue prefetch.
   • All data producer has a unified interface, you can compose and reuse them to perform complex preprocessing.

2. Callbacks, like tf.train.SessionRunHook, plugins, or extensions. Write a callback to implement everything you want to do apart from the training iterations, such as:

   • Change hyperparameters during training
   • Print some tensors of interest
   • Run inference on a test dataset
   • Run some operations once a while
   • Send loss to your phone

3. Model, or graph. models/ has some scoped abstraction of common models, but you can just use symbolic functions in tensorflow or slim/tflearn/tensorlayer/etc. LinearWrap and argscope simplify large models (e.g. vgg example).

With the above components defined, tensorpack trainer runs the training iterations for you. Even on a small CNN example, the training runs 2x faster than the equivalent Keras code.

Multi-GPU training is off-the-shelf by simply switching the trainer. You can also define your own trainer for different style of training (e.g. GAN).

Install:

Dependencies:

• Python 2 or 3
• TensorFlow >= 1.0.0
• Python bindings for OpenCV

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