Machine Learning
Est. read time: 1 minute | Last updated: December 17, 2024 by John Gentile
Contents
Overview
It is useful to review linear algebra concepts before continuing.
TBD reference [1]
Intro ML
Software and Platforms
TensorFlow
TensorFlow is one of the most popular platforms for Machine Learning development, protoyping and deployment.
TensorFlow Docker Container with GPU Support
Follow instructions at python-lib/tensorflow to install a Docker container with NVIDIA CUDA GPU support and common Jupyter & SciPy libraries.
TensorFlow Development
Other TensorFlow Resources
- instillai/TensorFlow-Course: some simple tutorials and Jupyter notebooks on getting started with TensorFlow.
- TensorFlow Hub: repository of hundreds of trained, ready-to-deploy machine learning models.
PyTorch
Jupyter Notebooks
For more info, see SciPy distribution in Python about installing Jupyter notebook support.
Another great tool which comes with most all dependencies/libraries ready to go is Google Colab, which allows you to store (in Google Drive), edit and run (even on GPU & TPU servers in some instances) Jupyter notebooks in the Google cloud environment.
Other Tools
- Horovod: Horovod is a distributed deep learning training framework for TensorFlow, Keras, PyTorch, and Apache MXNet
- MLPerf: ML benchmark results for various computing platforms.
- Caffe 2 is now a part of PyTorch
References
- [1]I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016 [Online]. Available at: http://www.deeplearningbook.org