• Stars
    star
    262
  • Rank 156,136 (Top 4 %)
  • Language
    Jupyter Notebook
  • License
    Apache License 2.0
  • Created about 7 years ago
  • Updated about 7 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Notes, Codes, and Tutorials for the Deep Learning Course <which I taught at ChinaHadoop>

Deep Learning Course Codes

Notes, Codes, and Tutorials for the Deep Learning Course at ChinaHadoop

注意每一份代码分别有Jupyter Notebook, Python, 以及HTML三种形式,大家可以按照自己的需求阅读,学习或运行。 运行时需要注意anaconda的版本问题,anaconda2-5.0.0与anaconda3-5.0.0分别对应python2.7与python3.6环境。

重要参考资料:

  1. Stanford CS229 Machine Learning, Fall 2017
  2. Deep Learning Book读书笔记
  3. Hands-on Machine Learning with Scikit-Learn and TensorFlow [book]

学习资料:

  1. Effective TensorFlow - TensorFlow tutorials and best practices.
  2. Finch - Many Machine Intelligence models implemented (mainly tensorflow, sometimes pytorch / mxnet)
  3. Pytorch Tutorials - PyTorch Tutorial for Deep Learning Researchers.
  4. MXNet the straight dope - An interactive book on deep learning. Much easy, so MXNet. Wow.

第一讲:深度学习课程总览与神经网络入门

代码示例:TensorFlow基础与线性回归模型(TensorFlow, PyTorch)

第二讲:传统神经网络

代码示例:K近邻算法,线性分类,以及多层神经网络(TensorFlow, PyTorch)

第三讲:卷积神经网络基础

代码示例:卷积神经网络的基础实现(TensorFlow)

第四讲:卷积神经网络进阶

代码示例:卷积神经网络的进阶实现(TensorFlow)

第五讲:深度神经网络:目标分类与识别

代码示例:深度神经网络-图像识别与分类(TensorFlow, PyTorch)

pip install git+https://github.com/zsdonghao/tensorlayer.git
conda install -c menpo opencv3 
或
pip install opencv-python
  • 所需数据集下载:data.zip: [微云][百度云] (覆盖./05_Image_recognition_and_classification/data文件夹)  
  • 所需模型下载: vgg19.npz  [微云][百度云] (放置于./05_Image_recognition_and_classification文件夹下)  
  • 所需模型下载:inception_v3.ckpt [微云][百度云] (放置于./05_Image_recognition_and_classification文件夹下)

第六讲:深度神经网络:目标检测与定位

代码示例:目标检测模型示例 (TensorFlow, PyTorch)

第七讲:深度神经网络:目标追踪与目标分割

代码示例:目标追踪与目标分割

第八讲:循环神经网络与序列模型

代码示例:循环神经网络

第九讲:无监督式学习与生成对抗网络

代码示例:生成对抗网络

第十讲:强化学习