Prerequisites

Installs

Before we begin looking at all things visual, there are a few packages necessary to install in order to complete the exercises for this week. As with the Audio module, it is strongly recommended that you set up a new conda environment with Python 3.7 or higher. You can create a new conda environment with many of the needed packaged by running

If you are on Windows or Linux, run:

conda create -n week2 python=3.8 jupyter notebook numpy matplotlib xarray numba bottleneck scipy opencv scikit-learn scikit-image pytorch torchvision cpuonly -c pytorch -c conda-forge

If you are on Mac OS run:

conda create -n week2 python=3.8 jupyter notebook numpy matplotlib xarray numba bottleneck scipy opencv scikit-learn scikit-image pytorch torchvision -c pytorch -c conda-forge

Make sure to activate this conda environment by running

conda activate week2

Now we will install Once the new environment is activated, install MyGrad, MyNN, Noggin, and Facenet, and cog_datasets, by running

pip install mygrad mynn noggin facenet-pytorch cog-datasets

Once the new environment is activated, install

• the Camera package, following the installation instructions detailed on GitHub.

• the Facenet-Models package, following the installation instructions detailed on GitHub.

If you choose not to create a new conda environment, make sure that the following packages are properly installed:

• jupyter

• notebook

• numpy

• matplotlib

• scipy

• opencv, which must be installed from the conda-forge channel

• pytorch, where specific installation instructions for your machine can be found here

• mygrad, which can be installed via pip

• mynn, which can be installed via pip

• noggin, which can be installed via pip

• facenet-pytorch, which can be installed via pip

• cog_datasets

• Camera

• Facenet-Models

Math Supplements

Before continuing in this module, it will be important to have a good understanding of the following materials:

• Fundamentals of Linear Algebra

• Introduction to Single-Variable Calculus

• Multivariable Calculus: Partial Derivatives & Gradients

• Chain Rule

It is strongly recommended reading through these sections and completing the reading comprehension questions before proceeding.