A neural net training interface based on TensorFlow.
See some examples to learn about the framework:
- Multi-GPU training of ResNet on ImageNet
- 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
- Deep Q-Network(DQN) variants on Atari games, including DQN, DoubleDQN, DuelingDQN.
- Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym
Examples are not only for demonstration of the framework -- you can train them and reproduce the results in papers.
It's Yet Another TF wrapper, but different in:
-
It's not a model wrapper.
- There are already too many symbolic function wrappers. Tensorpack includes only a few common models, but you can use any other model wrappers within tensorpack, such as sonnet/Keras/slim/tflearn/tensorlayer/....
-
Focus on training speed.
-
Speed comes for free with tensorpack -- it uses TensorFlow in the correct way. Even on a tiny CNN example, the training runs 1.6x faster than the equivalent Keras code.
-
Data-parallel multi-GPU training is off-the-shelf to use. It is as fast as Google's official benchmark.
-
Data-parallel distributed training is off-the-shelf to use. It is as slow as Google's official benchmark.
-
-
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 also naturally works with TF Queues or tf.data.
-
Interface of extensible Callbacks. Write a callback to implement everything you want to do apart from the training iterations, and enable it with one line of code. Common examples include:
- Change hyperparameters during training
- Print some tensors of interest
- Monitor GPU utilization
- Send error rate to your phone
See tutorials to know more about these features.
Dependencies:
- Python 2 or 3
- TensorFlow >= 1.0.0 (>=1.1.0 for Multi-GPU)
- Python bindings for OpenCV (Optional, but required by a lot of features)
pip install -U git+https://github.com/ppwwyyxx/tensorpack.git
# or add `--user` to avoid system-wide installation.
Besides, if you only want to use tensorpack.dataflow alone as a data processing library, TensorFlow is also optional.