Deep-Learning-Projects

Overview

A collection of Deep Learning projects made with TensorFlow, from Build Deep Learning Models with TensorFlow Skill Path from Codecademy. These projects cover the basics of neural networks, ranging from simple linear regression to convolutional neural networks.

Projects

• CNN X-Rays Lung Prediction: A deep learning model to predict lung conditions and abnormalities from chest X-ray images.
• Forest Cover Type Classification: A deep learning model classifier to predict the forest cover type based on cartographic variables.
• Regression with Graduate School Admissions Data: A deep learning regressor that predicts whether a student will be admitted to a graduate program based on percentage.
• Patient Survival Prediction: A deep learning model to predict patient survival based on medical data (e.g., whether the patient has diabetes or anemia, he or she smokes, age, etc.)
• Life Expectancy Prediction: A deep learning model to predict life expectancy based on various socio-economic factors.

Requirements

• Python
• scikit-learn
• TensorFlow
• NumPy
• Pandas
• Matplotlib
• seaborn

Getting Started

If you want to learn more about how to build neural networks with TensorFlow and how they work, feel free to use this project for learning purposes. Here's how to get started.

1. Download and install Python - You can visit Real Python to learn how to install Python on Windows/macOS/Linux.
2. Download and install Jupyter Notebook or Jupyter Lab - You can visit jupyter.org for more information. You can also install Anaconda, a distribution for Python and R that simplifies package management and deployment. Here's the link: anaconda.com
3. Clone the repository on your desired directory path - I recommend having this project on the Desktop or somewhere easily accessible.

cd Desktop
git clone https://github.com/WilhenAlbertoHM/Deep-Learning-Projects/
cd Deep-Learning-Projects
jupyter lab

Note: code . opens Visual Studio Code IDE. If you decide to use other IDEs, you can open the IDE of your choice and access the folder that way.

3. Install the required libraries to run the program (assuming you have Python installed). The commands below can be written inside your IDE's terminal:

pip install pandas
pip install numpy
pip install scikit-learn
pip install seaborn

4. You now can run the programs, whether they're .py or .ipynb files.

Acknowledgements

This project comes from the Codecademy course I'm currently taking: Build Deep Learning Models with TensorFlow. This was published on GitHub for educational purposes regarding the topics of machine learning.