Machine-Learning-Engineer-Capstone-Project

This is repository contains my capstone project Dog Breed Classification for the machine learing engineer nano degree

Project Goal

The goal of this project is to build a NN that can classfify humans and dogs, also predict the dog breed. The model can be used in any kind of applications such as mobile or web app. The model accepts an image from the user. The image can be of any shape. Then the model process the image and predict which kind of a dog it is. If the image contains a human then, it will provide an estimate of the dog breed that is most resembling.

The overall flow consists of the following steps:

1. Import Datasets
2. Detect a human
3. Detect a dog
4. Create a CNN to Classify Dog Breeds
5. Create a CNN to Classify Dog Breeds (using Transfer Learning)
6. Write your Algorithm
7. Test Your Algorithm

Make sure to download all datasets needed to train the model.

• Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dogImages.
• Download the human dataset. Unzip the folder and place it in the home diretcory, at location /lfw.

Repository

The original Udacity project instructions can be found here.

Dependencies

Click here for more information.

Click here for more details

Acknowledgments

I would like to thank Udacity for giving me this opportunity to work on an awesome project.