Deep Learning Guide - MNIST Dataset

This repository implements a step-by-step deep learning tutorial using TensorFlow and Keras, focused on the MNIST dataset.

1) Setup

This section covers environment setup for Windows and Linux.

Prerequisites

• Python 3.10+
• pip
• Git (optional, but recommended)

Clone the project

git clone git@github.com:gabrielSantosLima/deep_learning_guide.git
cd deep_learning_guide

---

Windows Setup (PowerShell)

1. Create virtual environment

python -m venv venv

2. Activate virtual environment

venv\Scripts\Activate.ps1

If script execution is blocked, run:

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

Then activate again.

3. Install dependencies

python -m pip install --upgrade pip
python -m pip install -r requirements.txt

4. Run setup doctor (interactive)

python doctor.py

5. Run setup doctor (non-interactive)

python doctor.py --non-interactive

---

Linux Setup (bash)

1. Create virtual environment

python3 -m venv venv

2. Activate virtual environment

source venv/bin/activate

3. Install dependencies

python -m pip install --upgrade pip
python -m pip install -r requirements.txt

4. Run setup doctor (interactive)

python doctor.py

5. Run setup doctor (non-interactive)

python doctor.py --non-interactive

---

What the Doctor checks

doctor.py validates the environment by:

• Checking Python version
• Checking if TensorFlow can detect GPU
• Running a tiny TensorFlow training with 3 examples to confirm runtime execution

If GPU is not detected, training can still run on CPU.

---

Next tutorial notebooks

• 00_Exploring_Dataset.ipynb
• 01_Training_And_Evaluating.ipynb
• 02_Deploy.ipynb