Setup Apple Silicon Mac for Machine Learning in 13 minutes (TensorFlow edition)

Daniel Bourke

How to get your Apple M1, M1 Pro, M1 Max or M1 Ultra Mac setup for data science and machine learning. In this video, we install Homebrew and Miniforge3 to create a Conda environment containing pandas, NumPy, Scikit-Learn, Matplotlib, Jupyter and TensorFlow.

We’ll also setup TensorFlow to leverage the GPU on the new M1 chips.

Step by step instructions –…
See M1 machine learning speed test benchmarks –
Setup Apple Silicon Mac with PyTorch –

Links: Learn ML (beginner-friendly courses I teach) –
ML courses/books I recommend –
Read my novel Charlie Walks –
Connect elsewhere: Web – T
witter –
Twitch –
ArXiv channel (past streams) –

Get email updates on my work –

0:00 – Intro
0:30 – What we’re covering
1:00 – All resources are on GitHub
1:25 – Downloading and installing Homebrew
2:45 – Downloading and installing Miniforge3
4:25 – Restart terminal for changes to take effect
4:57 – Creating a directory to test out TensorFlow
5:30 – Creating a Conda environment for machine learning experiments
7:12 – Installing TensorFlow dependencies for Mac from Apple’s Conda channel
8:40 – Installing tensorflow-macos
9:15 – Installing tensorflow-metal so you can run TensorFlow on your Mac’s GPU
10:30 – Installing tensorflow-datasets (optional)
10:50 – Installing standard data science packages (Jupyter, NumPy, pandas, Matplotlib, Sklearn)
11:15 – Starting a Jupyter Notebook
11:40 – Testing importing different libraries and seeing if TensorFlow has GPU access

#MachineLearning #MacBookPro

Leave a Comment