tensorpack 0.1.5

Neural Network Toolbox on TensorFlow

Neural Network Toolbox on TensorFlow

Docs & tutorials should be ready within a month. 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

• Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym

Unsupervised Learning:

• Generative Adversarial Network(GAN) variants, including DCGAN, InfoGAN, Conditional GAN, 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. Model, or graph. models/ has some scoped abstraction of common models, but you can simply use any symbolic functions available in tensorflow, or most functions in slim/tflearn/tensorlayer. LinearWrap and argscope simplify large models (vgg example).

2. DataFlow. tensorpack allows and encourages complex data processing.

   • All data producer has an unified interface, allowing them to be composed to perform complex preprocessing.

   • Use Python to easily handle any data format, yet still keep good performance thanks to multiprocess prefetch & TF Queue prefetch. For example, InceptionV3 can run in the same speed as the official code which reads data by TF operators.

3. Callbacks, including 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

With the above components defined, tensorpack trainer will run the training iterations for you. Multi-GPU training is off-the-shelf by simply switching the trainer. You can also define your own trainer for non-standard training (e.g. GAN).

Install:

Dependencies:

• Python 2 or 3

• TensorFlow >= 1.0.0rc0

• Python bindings for OpenCV

• (optional) use tcmalloc if running with large data

pip install --user -U git+https://github.com/ppwwyyxx/tensorpack.git
pip install --user -r opt-requirements.txt # (some optional dependencies required by certain submodules, you can install later if prompted)