TensorFlow Tutorials

中文翻译文件名以zh_CN或_CN结尾。

1. 简单线性模型(Notebook)

2. 卷积神经网络(Notebook)

3. Pretty Tensor (Notebook)

3-B. Layers API ([暂缺])

3-C. Keras API (Notebook)

4. 保存&回复 (Notebook)

5. 集成学习 (Notebook)

6. CIFAR-10 (Notebook)

7. Inception模型 (Notebook)

8. 迁移学习 (Notebook)

9. 视频数据 (Notebook)

10. 微调 (Notebook)

11. 对抗样本 (Notebook)

12. MNIST的对抗样本 (Notebook)

13. 可视化分析 (Notebook)

13-B. MNIST的可视化分析 ([暂缺])

14. DeepDream (Notebook)

15. 风格迁移 (Notebook)

16. 强化学习 ([暂缺])

17. Estimator API (Notebook)

18. TFRecords & Dataset API (Notebook)

19. 超参数优化 (Notebook)

20. 自然语言处理 (Notebook)

21. 机器翻译 (Notebook)

22. 图像描述 (Notebook)

23. 时间序列预测 (Notebook)

---

Original repository on GitHub

Original author is Magnus Erik Hvass Pedersen

Introduction

• These tutorials are intended for beginners in Deep Learning and TensorFlow.
• Each tutorial covers a single topic.
• The source-code is well-documented.
• There is a YouTube video for each tutorial.

Tutorials

1. Simple Linear Model (Notebook)

2. Convolutional Neural Network (Notebook)

3. Pretty Tensor (Notebook)

3-B. Layers API (Notebook)

3-C. Keras API (Notebook)

4. Save & Restore (Notebook)

5. Ensemble Learning (Notebook)

6. CIFAR-10 (Notebook)

7. Inception Model (Notebook)

8. Transfer Learning (Notebook)

9. Video Data (Notebook)

10. Fine-Tuning (Notebook)

11. Adversarial Examples (Notebook)

12. Adversarial Noise for MNIST (Notebook)

13. Visual Analysis (Notebook)

13-B. Visual Analysis for MNIST (Notebook)

14. DeepDream (Notebook)

15. Style Transfer (Notebook)

16. Reinforcement Learning (Notebook)

17. Estimator API (Notebook)

18. TFRecords & Dataset API (Notebook)

19. Hyper-Parameter Optimization (Notebook)

20. Natural Language Processing (Notebook)

21. Machine Translation (Notebook)

22. Image Captioning (Notebook)

23. Time-Series Prediction (Notebook)

Videos

These tutorials are also available as YouTube videos.

Obsolete Tutorials

Some of these tutorials use an API called PrettyTensor for creating Neural Networks in TensorFlow, but the PrettyTensor API is now obsolete. Some of the Notebooks are therefore also obsolete and they are clearly marked at the top of each Notebook. It is recommended that you instead use the Keras API for creating Neural Networks in TensorFlow.

Forks

See the selected list of forks for community modifications to these tutorials.

Downloading

Some of the Python Notebooks use source-code located in different files to allow for easy re-use across multiple tutorials. It is therefore recommended that you download the whole repository from GitHub, instead of just downloading the individual Python Notebooks.

Git

The easiest way to download and install these tutorials is by using git from the command-line:

git clone https://github.com/Hvass-Labs/TensorFlow-Tutorials.git

This will create the directory TensorFlow-Tutorials and download all the files to it.

This also makes it easy to update the tutorials, simply by executing this command inside that directory:

git pull

Zip-File

You can also download the contents of the GitHub repository as a Zip-file and extract it manually.

Installation

There are different ways of installing and running TensorFlow. This section describes how I did it for these tutorials. You may want to do it differently and you can search the internet for instructions.

If you are new to using Python and Linux, etc. then this may be challenging to get working and you may need to do internet searches for error-messages, etc. It will get easier with practice.

Python Version 3.5 or Later

These tutorials were developed on Linux using Python 3.5 / 3.6 (the Anaconda distribution) and PyCharm.

There are reports that Python 2.7 gives error messages with these tutorials. Please make sure you are using Python 3.5 or later!

Environment

After installing Anaconda, you should create a conda environment so you do not destroy your main installation in case you make a mistake somewhere:

conda create --name tf python=3

Now you can switch to the new environment by running the following (on Linux):

source activate tf

Required Packages

The tutorials require several Python packages to be installed. The packages are listed in requirements.txt First you need to edit this file and select whether you want to install the CPU or GPU version of TensorFlow.

To install the required Python packages and dependencies you first have to activate the conda-environment as described above, and then you run the following command in a terminal:

pip install -r requirements.txt

Note that the GPU-version of TensorFlow also requires the installation of various NVIDIA drivers, which is not described here.

Testing

You should now be able to run the tutorials in the Python Notebooks:

cd ~/development/TensorFlow-Tutorials/  # Your installation directory.
jupyter notebook

This should start a web-browser that shows the list of tutorials. Click on a tutorial to load it.

License (MIT)

These tutorials and source-code are published under the MIT License which allows very broad use for both academic and commercial purposes.

A few of the images used for demonstration purposes may be under copyright. These images are included under the "fair usage" laws.

You are very welcome to modify these tutorials and use them in your own projects. Please keep a link to the original repository.