First, you must have your Python enviroment for deep learning. You can
install miniconda and create that enviroment. See

https://docs.conda.io/en/latest/miniconda.html

For instance, in Ubuntu 20.04 or above, you may want to download
Miniconda3-py312_24.5.0-0-Linux-x86_64.sh and execute (or a newer
version with python 3.13, for instance)

ssh Miniconda3-py312_24.5.0-0-Linux-x86_64.sh

to install miniconda with Python 3.12 in your 64-bit machine.

A new environment for mo433 in conda can be created by

conda env create -f environment.yml

You may use

conda activate mo433

to activate this environment, or 

conda deactivate

to deactivate it.

The environment.yml already comes with the needed packages so far, but if you
need to install a package, follow the instructions below.

conda install <package-name>

Similarly, you may unsinstall packages by typing

conda uninstall <package-name>

For pytorch, it is better to follow instructions at
https://pytorch.org/

For instance, to install it with cuda toolkit for execution in the GPU
of your machine, the command will be

conda install pytorch torchvision -c pytorch -c nvidia
conda install -c nvidia cudatoolkit

For some packages, such as torch-summary and torch-snippets, you might
have to use

pip install torch-summary
pip install torch-snippets

Have fun!
