Module 0 — Environment Setup (Beginner Guide)

Deep Learning Tutorial Series

• Module 0 — Environment Setup (Beginner Guide)
• Module 1 — Machine Learning & Neural Network Basics
• Module 2 — Training & Learning Process
• Module 3 — Practical Deep Learning with PyTorch
• Module 4 — CNNs and Computer Vision
• Module 5 — Sequence Models + Modern Deep Learning Overview

This guide helps you set up a working Python environment for deep learning using PyTorch. After completing this module, you will be able to run neural network code locally or in notebook environments.

0.1 What You Will Achieve

By the end of this setup:

• Python is installed correctly
• A clean environment is created
• PyTorch is installed and verified
• Jupyter Notebook or VS Code is ready
• A simple tensor operation runs successfully

0.3 Install Python Environment

Using Anaconda / Miniconda. Best for beginners due to easy package management.

Step 1: Install Miniconda

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

Verify installation:

conda --version

Expected output:

conda 23.x.x

Step 2: Create a New Environment

Create environment:

conda create -n dl python=3.10 -y

Activate it:

conda activate dl

Check Python version:

python --version

Expected:

Python 3.10.x

0.4 Install Core Tools

Install Jupyter Notebook

conda install jupyter -y

Start notebook:

jupyter notebook

OR install JupyterLab (recommended):

conda install jupyterlab -y
jupyter lab

Install VS Code (Recommended)

Download: https://code.visualstudio.com/

Install extensions:

• Python (Microsoft)
• Jupyter

0.5 Install PyTorch

Official selector: https://pytorch.org/get-started/locally/

select the right installation according to your OS, and compute platform.

0.6 Verify Installation

Open Python:

python

Run:

import torch

print("PyTorch version:", torch.__version__)
print("CUDA available:", torch.cuda.is_available())

x = torch.tensor([1.0, 2.0, 3.0])
print("Tensor:", x)
print("Sum:", x.sum())

Expected output:

PyTorch version: x.x.x
CUDA available: False (or True)
Tensor: tensor([1., 2., 3.])
Sum: tensor(6.)

0.7 First Jupyter Notebook Test

Start notebook:

jupyter notebook

Run in a cell:

import torch

a = torch.randn(2, 3)
b = torch.randn(2, 3)

print(a + b)

If output appears, setup is successful.

0.8 Common Issues & Fixes

Issue 1: conda not found

• Restart terminal
• Reinstall Miniconda
• Ensure PATH is configured

Issue 2: torch import error

pip uninstall torch -y
pip install torch torchvision torchaudio

Issue 3: CUDA not detected

• No NVIDIA GPU OR CPU-only install is used
• This is fine for beginners

Issue 4: Jupyter not launching

conda install notebook

or

pip install notebook

0.9 Optional (Advanced)

Export environment

conda env export > dl_env.yml

Restore environment

conda env create -f dl_env.yml

Virtual environment alternative

python -m venv dl

Activate:

Windows

dl\Scripts\activate

Linux/Mac

source dl/bin/activate

Install dependencies:

pip install torch torchvision torchaudio jupyter

0.10 Final Checklist

Before moving on, ensure:

• Environment activates successfully
• Python runs
• PyTorch imports correctly
• Tensor operations work
• Jupyter launches
• No installation errors

Acknowledgement

Part of the contents are generated by ChatGPT.

Return to the Main Page of Deep Learning and Machine Learning .