Introduction
This course focuses on supervised machine learning. Two areas of machine learning we do not cover involve self-supervised learning and reinforcement learning.
Setup
We use the following packages:
numpy
: working with \(n\)-D arraystorch
: training of differentiable modelstorchvision
: tools for vision modelspandas
: working with datamatplotlib
: plottingtqdm
: progress bars in the command linescikit-learn
: source some classic datasets
The following command uses pip
to install these python
packages:
pip install torch torchvision numpy matplotlib tqdm pandas scikit-learn
Virtual Environment
Virtual environments allow you to install a custom set of packages with custom package versions for a project.
Inside the dlcourse
directory, run
python -m venv code-venv
to create a blank virtual environment.
Activate it, and then install packages. Upon activation, the command line prompt changes to start with the name of the virtual environment. Here, it would be (code-venv)
:
source code-venv/bin/activate
pip install torch torchvision numpy matplotlib tqdm pandas scikit-learn
When you are done, you can run deactivate
to return to the default global environment.
NumPy
A nice overview of using numpy
is located online here.
Two KEY issues to watch out for:
- Standard matrix multiplication in
numpy
uses the@
symbol, not the*
symbol. Users coming fromMatlab
orJulia
often trip over this issue a few times until they internalize the new symbol. - 2D Arrays are stored in row-major form.