Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/MLEveryday/practicalAI-cn

AI实战-practicalAI 中文版
https://github.com/MLEveryday/practicalAI-cn

deep-learning google-colab-notebook jupyter-notebook machine-learning pytorch

Last synced: 3 months ago
JSON representation

AI实战-practicalAI 中文版

Host: GitHub
URL: https://github.com/MLEveryday/practicalAI-cn
Owner: MLEveryday
License: mit
Created: 2018-12-11T09:40:16.000Z (almost 6 years ago)
Default Branch: master
Last Pushed: 2023-12-31T19:26:09.000Z (10 months ago)
Last Synced: 2024-06-12T08:55:56.515Z (5 months ago)
Topics: deep-learning, google-colab-notebook, jupyter-notebook, machine-learning, pytorch
Language: Jupyter Notebook
Homepage:
Size: 10.7 MB
Stars: 3,234
Watchers: 160
Forks: 735
Open Issues: 5
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # AI实战-[practicalAI](https://github.com/LisonEvf/practicalAI-cn) 中文版

[![Colab](https://img.shields.io/badge/launch-Google%20Colab-orange.svg)](https://colab.research.google.com/)

[![MIT](https://img.shields.io/badge/license-MIT-brightgreen.svg)](https://github.com/LisonEvf/practicalAI-cn/blob/master/LICENSE)

[![Author](https://img.shields.io/badge/Author-GokuMohandas-blue.svg)](https://github.com/GokuMohandas)

[![Fork](https://img.shields.io/badge/Fork-MLEveryday/practicalAI--cn-yellow.svg)](https://github.com/MLEveryday/practicalAI-cn)

让你有能力使用机器学习从数据中获取有价值的见解。

- 🔥 使用 [PyTorch](https://pytorch.org/) 实现基本的机器学习算法和深度神经网络。

- 🖥️ 不需要任何设置，在浏览器中使用 [Google Colab](https://colab.research.google.com/) 运行所有程序。

- 📦 不仅仅是教程，而是学习产品级的面向对象机器学习编程。

## Notebooks

|基础|深度学习|进阶|主题|

|-|-|-|-|

|📓 [Notebooks](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/00_Notebooks.ipynb)|🔥 [PyTorch](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/07_PyTorch.ipynb)|📚 [高级循环神经网络 Advanced RNNs](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/14_Advanced_RNNs.ipynb)|📸 [计算机视觉 Computer Vision](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/15_Computer_Vision.ipynb)|

|🐍 [Python](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/01_Python.ipynb)|🎛️ [多层感知 Multilayer Perceptrons](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/08_Multilayer_Perceptron.ipynb)|🏎️ Highway and Residual Networks|⏰ 时间序列分析 Time Series Analysis|

|🔢 [NumPy](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/02_NumPy.ipynb)|🔎 [数据和模型 Data & Models](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/09_Data_and_Models.ipynb)|🔮 自编码器 Autoencoders|🏘️ Topic Modeling|

| 🐼 [Pandas](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/03_Pandas.ipynb) |📦 [面向对象的机器学习 Object-Oriented ML](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/10_Object_Oriented_ML.ipynb)|🎭 生成对抗网络 Generative Adversarial Networks|🛒 推荐系统 Recommendation Systems|

|📈 [线性回归 Linear Regression](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/04_Linear_Regression.ipynb)|🖼️ [卷积神经网络 Convolutional Neural Networks](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/11_Convolutional_Neural_Networks.ipynb)|🐝 空间变换模型 Spatial Transformer Networks|🗣️ 预训练语言模型 Pretrained Language Modeling|

|📊 [逻辑回归 Logistic Regression](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/05_Logistic_Regression.ipynb)|📝 [嵌入层 Embeddings](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/12_Embeddings.ipynb)||🤷 多任务学习 Multitask Learning|

|🌳 [随机森林 Random Forests](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/06_Random_Forests.ipynb)|📗 [递归神经网络 Recurrent Neural Networks](https://nbviewer.jupyter.org/github/LisonEvf/practicalAI-cn/blob/master/notebooks/13_Recurrent_Neural_Networks.ipynb)||🎯 Low Shot Learning|

|💥 k-均值聚类 KMeans Clustering|||🍒 强化学习 Reinforcement Learning|

## 查看 notebooks

如果不需要运行 notebooks，使用 Jupyter nbviewer 就可以方便地查看它们。

将 `https://github.com/` 替换为 `https://nbviewer.jupyter.org/github/` ，或者打开 `https://nbviewer.jupyter.org` 并输入 notebook 的 URL。

## 运行 notebooks

1. 在本项目的 [`notebooks`](/notebooks/) 文件夹获取 notebook；

2. 你可以在 Google Colab（推荐）或本地电脑运行这些 notebook；

3. 点击一个 notebook，然后替换URL地址中 `https://github.com/` 为 `https://colab.research.google.com/github/` ，或者使用这个 [Chrome扩展](https://chrome.google.com/webstore/detail/open-in-colab/iogfkhleblhcpcekbiedikdehleodpjo) 一键完成；

4. 登录你自己的 Google 账户；

5. 点击工具栏上的 `复制到云端硬盘`，会在一个新的标签页打开 notebook；



5. 通过去掉标题中的`副本`完成 notebook 重命名；

6. 运行代码、修改等，所有这些都会自动保存到你的个人 Google Drive。

## 贡献 notebooks

1. 修改后下载 Google Colab notebook 为 .ipynb 文件；



2. 转到 https://github.com/LisonEvf/practicalAI-cn/tree/master/notebooks ；

3. 点击 `Upload files`.



5. 上传这个 .ipynb 文件；

6. 写一个详细详细的提交标题和说明；

7. 适当命名你的分支；

8. 点击 `Propose changes`。



## 贡献列表

欢迎任何人参与和完善。

|Notebook|译者|

|--|--|

|00_Notebooks.ipynb|[@amusi](https://github.com/amusi)|

|01_Python.ipynb|[@amusi](https://github.com/amusi)|

|02_NumPy.ipynb|[@amusi](https://github.com/amusi)|

|03_Pandas.ipynb|[@amusi](https://github.com/amusi)|

|04_Linear_Regression.ipynb|[@jasonhhao](https://github.com/jasonhhao)|

|05_Logistic_Regression.ipynb|[@jasonhhao](https://github.com/jasonhhao)|

|06_Random_Forests.ipynb|[@jasonhhao](https://github.com/jasonhhao)|

|07_PyTorch.ipynb|[@amusi](https://github.com/amusi)|

|08_Multilayer_Perceptron.ipynb|[@zhyongquan](https://github.com/zhyongquan)|

|09_Data_and_Models.ipynb|[@zhyongquan](https://github.com/zhyongquan)|

|10_Object_Oriented_ML.ipynb|[@zhyongquan](https://github.com/zhyongquan)|

|11_Convolutional_Neural_Networks.ipynb||

|12_Embeddings.ipynb|[@wengJJ](https://github.com/wengJJ)|

|13_Recurrent_Neural_Networks.ipynb||

|14_Advanced_RNNs.ipynb||

|15_Computer_Vision.ipynb|||