Note
Our goal is to build a machine learning algorithm capable of detecting the correct animal (cat or dog) in new unseen images. So we are trying to solve a classification problem. In this project, I have write an algorithm to classify whether images contain either a dog or a cat. Our algorithm has images as input and return whether image contains dogs or cats. In this Capstone, we have resolved a project from kaggle competition and using a dataset from Kaggle. In this project we have applied Convolutional Neural Network(CNN) to predict whether images contains dogs or cats. CNN is used here because CNN are widely used for images classification task.
This project requires Python 2.7 and the following Python libraries installed:
- NumPy
- Pandas
- matplotlib
- OpenCv
- scikit-learn
- Keras
- Tensorflow
You will also need to have software installed to run and execute a Jupyter Notebook. In a terminal or command window, navigate to the top-level project directory capstone-project/ (that contains this README) and run one of the following commands:
jupyter notebook boston_housing.ipynb
You will need to first download the dataset from https://www.kaggle.com/c/dogs-vs-cats/data.
Enjoy.