The project aims to build a dog breed classifier which aims to distinguish between 133 different dog's breed.
It is used two different approaches. A first Convolutional Neural Network built from scratch and a Vgg16 pre-trained on ImageNet dataset and modified for increasing the performance.
Additionally, it is added a human detector. It will match your photo to the dog breed that is more close to you.
It is suggested to use virtualenv (https://docs.python.org/3/tutorial/venv.html)
Then use pip to install the requirement:
pip install -r requirement.txt
This project is just for your reference and fun purposes. Additionally, I share it as a portfolio of my work.