TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides an extensive collection of customizable neural layers to build complex AI models. TensorLayer is awarded the 2017 Best Open Source Software by the ACM Multimedia Society. TensorLayer can also be found at iHub and Gitee.

🔥📰🔥 Reinforcement Learning Model Zoos: Low-level APIs for Research and High-level APIs for Production

🔥📰🔥 Sipeed Maxi-EMC: Run TensorLayer models on the low-cost AI chip (e.g., K210) (Alpha Version)

🔥📰🔥 NNoM: Run TensorLayer quantized models on the MCU (e.g., STM32) (Coming Soon)

TensorLayer is a new deep learning library designed with simplicity, flexibility and high-performance in mind.

• Simplicity : TensorLayer has a high-level layer/model abstraction which is effortless to learn. You can learn how deep learning can benefit your AI tasks in minutes through the massive examples.
• Flexibility : TensorLayer APIs are transparent and flexible, inspired by the emerging PyTorch library. Compared to the Keras abstraction, TensorLayer makes it much easier to build and train complex AI models.
• Zero-cost Abstraction : Though simple to use, TensorLayer does not require you to make any compromise in the performance of TensorFlow (Check the following benchmark section for more details).

TensorLayer is NOT yet another library in the TensorFlow world. Other wrappers like Keras and TFLearn hide many powerful features of TensorFlow and provide little support for writing custom, complex AI models. Inspired by PyTorch, TensorLayer APIs are simple, flexible and most importantly, pythonic. TensorLayer has a fast-growing community. It has been used by researchers and engineers all over the world, including those from Peking University, Imperial College London, UC Berkeley, Carnegie Mellon University, Stanford University, and companies like Google, Microsoft, Alibaba, Tencent, Xiaomi, and Bloomberg.

TensorLayer has extensive documentation for both beginners and professionals. The documentation is available in both English and Chinese.

If you want to try the experimental features on the the master branch, you can find the latest document here.

You can find a large collection of tutorials, examples and real-world applications using TensorLayer within examples or through the following space:

TensorLayer 2.0 relies on TensorFlow, numpy, and others. To use GPUs, CUDA and cuDNN are required.

Install TensorFlow:

pip3 install tensorflow-gpu==2.0.0-rc1 # TensorFlow GPU (version 2.0 RC1) pip3 install tensorflow # CPU version

Install the stable release of TensorLayer:

pip3 install tensorlayer

Install the unstable development version of TensorLayer:

pip3 install git+https://github.com/tensorlayer/tensorlayer.git

If you want to install the additional dependencies, you can also run

pip3 install --upgrade tensorlayer[all] # all additional dependencies pip3 install --upgrade tensorlayer[extra] # only the `extra` dependencies pip3 install --upgrade tensorlayer[contrib_loggers] # only the `contrib_loggers` dependencies

If you are TensorFlow 1.X users, you can use TensorLayer 1.X:

# For last stable version of TensorLayer 1.X pip3 install --upgrade tensorlayer==1.X

The following table shows the training speeds of VGG16 using TensorLayer and native TensorFlow on a TITAN Xp.

Please read the Contributor Guideline before submitting your PRs.

If you use TensorLayer for any projects, please cite this paper：

@article{tensorlayer2017, author = {Dong, Hao and Supratak, Akara and Mai, Luo and Liu, Fangde and Oehmichen, Axel and Yu, Simiao and Guo, Yike}, journal = {ACM Multimedia}, title = {{TensorLayer: A Versatile Library for Efficient Deep Learning Development}}, url = {http://tensorlayer.org}, year = {2017} } 

TensorLayer is released under the Apache 2.0 license.