Computer Vision demo for the DataHour webinar series using PyTorch.

Run the Computer Vision Demo in a colab notebook

⚠ Colab provides a temporary environment: anything you do will be deleted after a while, so make sure you download any data you care about.

• PyTorch
• Fashion MNIST GitHub repo
• Deep Learning with Python, Second Edition

• Google Slides

To ensure our project runs smoothly on your local machine, we'll set up a dedicated Python environment and install the necessary packages.

• Python (we're using Python 3 for this project)
• pip (Python package installer)
• Either virtualenv or conda (based on your preference)

First, install Anaconda or Miniconda based on your operating system.

Then, create a new environment:

conda create --name myenv

Activate the environment:

conda activate myenv

You can skip this step if you completed the previous step using Conda.

pip install virtualenv
virtualenv myenv
.\myenv\Scripts\activate

pip3 install virtualenv
virtualenv myenv
source myenv/bin/activate

There is a requirements.txt file that lists all the necessary packages for this demo.

If you're using Conda, while most of the packages are available directly through pip, some might have better support or performance when installed through Conda channels:

conda install --file requirements.txt

Otherwise, install the packages using pip:

pip install -r requirements.txt

Your environment is now set up with all the necessary packages. You can proceed with running or developing the project.