Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility
https://github.com/tensorpack/tensorpack
deep-learning machine-learning neural-networks reinforcement-learning tensorflow
Last synced: 26 days ago
JSON representation
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility
- Host: GitHub
- URL: https://github.com/tensorpack/tensorpack
- Owner: tensorpack
- License: apache-2.0
- Created: 2015-12-25T23:08:44.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2023-08-06T00:30:36.000Z (over 1 year ago)
- Last Synced: 2024-06-24T04:56:02.029Z (5 months ago)
- Topics: deep-learning, machine-learning, neural-networks, reinforcement-learning, tensorflow
- Language: Python
- Homepage:
- Size: 8.67 MB
- Stars: 6,296
- Watchers: 197
- Forks: 1,813
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGES.md
- License: LICENSE
Awesome Lists containing this project
- awesome - tensorpack - A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility (Python)
- awesome-python-machine-learning-resources - GitHub - 0% open · ⏱️ 04.05.2022): (机器学习框架)
- awesome-list - Tensorpack - A high-level deep learning library based on TensorFlow. (Deep Learning Framework / High-Level DL APIs)
- awesome-datascience - tensorpack
README
Tensorpack is a neural network training interface based on graph-mode TensorFlow.
[](http://tensorpack.readthedocs.io)
[](https://gitter.im/tensorpack/users)
[](http://models.tensorpack.com)
## Features:
It's Yet Another TF high-level API, with the following highlights:
1. Focus on __training speed__.
+ Speed comes for free with Tensorpack -- it uses TensorFlow in the __efficient way__ with no extra overhead.
On common CNNs, it runs training [1.2~5x faster](https://github.com/tensorpack/benchmarks/tree/master/other-wrappers) than the equivalent Keras code.
Your training can probably gets faster if written with Tensorpack.
+ Scalable data-parallel multi-GPU / distributed training strategy is off-the-shelf to use.
See [tensorpack/benchmarks](https://github.com/tensorpack/benchmarks) for more benchmarks.
2. Squeeze the best data loading performance of Python with [`tensorpack.dataflow`](https://github.com/tensorpack/dataflow).
+ Symbolic programming (e.g. `tf.data`) [does not](https://tensorpack.readthedocs.io/tutorial/philosophy/dataflow.html#alternative-data-loading-solutions)
offer the data processing flexibility needed in research.
Tensorpack squeezes the most performance out of __pure Python__ with various autoparallelization strategies.
3. Focus on reproducible and flexible research:
+ Built and used by researchers, we provide high-quality [reproducible implementation of papers](https://github.com/tensorpack/tensorpack#examples).
4. It's not a model wrapper.
+ There are too many symbolic function wrappers already. Tensorpack includes only a few common layers.
You can use any TF symbolic functions inside Tensorpack, including tf.layers/Keras/slim/tflearn/tensorlayer/....
See [tutorials and documentations](http://tensorpack.readthedocs.io/tutorial/index.html#user-tutorials) to know more about these features.
## Examples:
We refuse toy examples.
Instead of showing tiny CNNs trained on MNIST/Cifar10,
we provide training scripts that reproduce well-known papers.
We refuse low-quality implementations.
Unlike most open source repos which only __implement__ papers,
[Tensorpack examples](examples) faithfully __reproduce__ papers,
demonstrating its __flexibility__ for actual research.
### Vision:
+ [Train ResNet](examples/ResNet) and [other models](examples/ImageNetModels) on ImageNet
+ [Train Mask/Faster R-CNN on COCO object detection](examples/FasterRCNN)
+ [Unsupervised learning with Momentum Contrast](https://github.com/ppwwyyxx/moco.tensorflow) (MoCo)
+ [Adversarial training with state-of-the-art robustness](https://github.com/facebookresearch/ImageNet-Adversarial-Training)
+ [Generative Adversarial Network(GAN) variants](examples/GAN), including DCGAN, InfoGAN, Conditional GAN, WGAN, BEGAN, DiscoGAN, Image to Image, CycleGAN
+ [DoReFa-Net: train binary / low-bitwidth CNN on ImageNet](examples/DoReFa-Net)
+ [Fully-convolutional Network for Holistically-Nested Edge Detection(HED)](examples/HED)
+ [Spatial Transformer Networks on MNIST addition](examples/SpatialTransformer)
+ [Visualize CNN saliency maps](examples/Saliency)
### Reinforcement Learning:
+ [Deep Q-Network(DQN) variants on Atari games](examples/DeepQNetwork), including DQN, DoubleDQN, DuelingDQN.
+ [Asynchronous Advantage Actor-Critic(A3C) with demos on OpenAI Gym](examples/A3C-Gym)
### Speech / NLP:
+ [LSTM-CTC for speech recognition](examples/CTC-TIMIT)
+ [char-rnn for fun](examples/Char-RNN)
+ [LSTM language model on PennTreebank](examples/PennTreebank)
## Install:
Dependencies:
+ Python 3.3+.
+ Python bindings for OpenCV. (Optional, but required by a lot of features)
+ TensorFlow ≥ 1.5
* TF is not not required if you only want to use `tensorpack.dataflow` alone as a data processing library
* When using TF2, tensorpack uses its TF1 compatibility mode. Note that a few examples in the repo are not yet migrated to support TF2.
```
pip install --upgrade git+https://github.com/tensorpack/tensorpack.git
# or add `--user` to install to user's local directories
```
Please note that tensorpack is not yet stable.
If you use tensorpack in your code, remember to mark the exact version of tensorpack you use as your dependencies.
## 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}
}
```