j-cabin/awesome-ml-tools

Organize some useful tools for machine learning.

Awesome-ML-Tools

Why did I create this project:

1. There are many projects that summarize machine learning materials and courses, but there are not many projects that summarize machine learning tools.
2. I read 《ARTIFICIAL INTELLIGENCE 101》, which introduces some tools. So an idea hit me that organizes more useful tools from time to time.

Development Environment

Note: For the GPU selection section, 《Which GPU(s) to Get for Deep Learning》 is very well written. This article was also translated into Chinese version in April 2019.

1. Google Colab: Online deep learning platform.
2. JupyterLab: Enhanced version of Jupyter Notebook.
3. DeepmindLab: AI training experimental platform.
4. Nextjournal: Experimental platform with templates, multi-language, version control, multi-person collaboration, GPU available, online help and other functions.

Development Tools

1. xg2xg: A collection of development tools summarized by Googler.
2. aiXcoder: Tensorflow code auto-complete plugin (for PyCharm).
3. nbextensions: Jupyter Notebook plugin collection.
4. jupytext: Support multi-format export, Jupyter Notebook and IDE jointly develop tool.
5. Awesome-pytorch-list: Pytorch common library collection.

Dataset Annotation Tools

1. LabelImg: Target detection (picture) annotation tool.
2. Colabeler: Support for various annotation forms such as image/text/video.
3. LC-Finder: Image management tool that supports image annotation and target detection.

Auto-ML

1. NNI: a lightweight but powerful toolkit to help users automate Feature Engineering, Neural Architecture Search, Hyperparameter Tuning and Model Compression.
2. Optuna: an automatic hyperparameter optimization software framework, particularly designed for machine learning.
3. SHERPA: a Python library for hyperparameter tuning of machine learning models.
4. BOML: A Bilevel Optimization Library in Python for Meta Learning.

Visualization

1. Tensorflow Playground: One of the Tensorflow toolset, using a browser to experience neural networks.
2. TensorSpace: A 3D visualization framework for building neural networks.
3. Embedding Projector: Google's open source high-dimensional data visualization tool.
4. Netron: Model structure visualization.
5. PythonTutor: Code visualization (Python, JS, Ruby, etc.).
6. Visualgo: Data structure visualization.
7. USF/Algomation/Algorithm Visualizer: Algorithm visualization.
8. Graph Editor: Graph theory board.
9. Netscope: Quickly draw neural network structures (flexibly).
10. NN SVG: Quickly plot neural networks for FCNN, LeNet, and AlexNet (SVG version).
11. ConvNetDraw: Quick Draw CNN (low resolution).
12. PlotNeuralNet: Neural network drawing code (LaTeX).
13. draw_convnet: Neural network drawing code (Python).
14. scikit-plot: Quickly draw machine learning related charts.

Programming Language

1. Awesome Data Science with Python: Use Python to play data science resources (libraries, handouts, code snippets, blogs, etc.)
2. Data Science Cheatsheets: List of Data Science Cheatsheets.
3. Ubuntu Pastebin: Publish the code for easy reading.
4. Try It Online: An online compiler that can share code and support hundreds of languages.
5. Dooccn: Online compiler for various common languages.
6. CodeIf: Let your variable naming no longer tangled.

Dataset

1. Datasetlist: Collect various data sets such as CV, NLP, QA, and Audio.
2. Dataset Search: Google's dataset search engine.
3. Awesome-public-dataset: A topic-centric list of HQ open datasets.
4. RecommenderSystem-DataSet: Recommended System dataset.
5. Citation Network Dataset: DBLP/ACM citation data set.
6. Data-SNA: Datasets for Social Network Analysis.
7. Ai-Yanxishe: The data set (various types) collected by the AI Institute.
8. Aistudio-dataset: A public data set aggregated by Baidu.
9. Kaggle: Kaggle dataset.
10. TensorFlow: The data set provided by Tensorflow.
11. OpenCorporates: The world's largest company open dataset.
12. Datagv(U.S.): US government open data.
13. Datagv(U.K.): UK government open data.
14. Health Data: Medical sanitation data set.
15. CDC: Health disease control data set.
16. The World Factbook: Information data for countries around the world.
17. Pew Internet: Sociological data set.

Paper

1. Papers with code: Find the paper corresponding to open source code.
2. Papers with code (Sorted by stars): All papers from the AI field from 2013-2018 were collected and sorted according to the number of stars on GitHub.
3. bestofml: Selected books/courses/recruitment sites/news blogs/papers in the field of machine learning.
4. arXiv: The pre-printed website of the paper.
5. arxiv-sanity-preserver: Arxiv paper classification, search and filtering.
6. Overleaf: Online LaTeX editor.
7. autoreject: Automatically generate paper review comments.
8. Catalyzex: Link all AI/ML Papers with Code.
9. Papers-with-video: find video for arxiv papers.

Note: If you are interested in this project, please keep your attention and welcome to complete it.