Welcome to TensorLayer¶
TensorLayer is a Deep Learning (DL) and Reinforcement Learning (RL) library extended from Google TensorFlow. It provides popular DL and RL modules that can be easily customized and assembled for tackling real-world machine learning problems.
Note
If you got problem to read the docs online, you could download the repository
on GitHub, then go to /docs/_build/html/index.html to read the docs
offline. The _build folder can be generated in docs using make html.
User Guide¶
The TensorLayer user guide explains how to install TensorFlow, CUDA and cuDNN, how to build and train neural networks using TensorLayer, and how to contribute to the library as a developer.
API Reference¶
If you are looking for information on a specific function, class or method, this part of the documentation is for you.
- API - Layers
- Understand Basic layer
- Understand Dense layer
- Your layer
- Layer list
- Name Scope and Sharing Parameters
- Basic layer
- Input layer
- One-hot layer
- Word Embedding Input layer
- Dense layer
- Noise layer
- Convolutional layer (Pro)
- Convolutional layer (Simplified)
- Pooling layer
- Padding layer
- Normalization layer
- Time distributed layer
- Fixed Length Recurrent layer
- Advanced Ops for Dynamic RNN
- Dynamic RNN layer
- Sequence to Sequence
- Shape layer
- Lambda layer
- Merge layer
- Extend layer
- Estimator layer
- Connect TF-Slim
- Connect Keras
- Parametric activation layer
- Flow control layer
- Wrapper
- Helper functions
- API - Cost
- API - Preprocessing
- API - Iteration
- API - Utility
- API - Natural Language Processing
- API - Reinforcement Learning
- API - Load, Save Model and Data
- API - Visualize Model and Data
- API - Operation System
- API - Activations
- API - Database