building-image-classifier

DSND Term 1 Project: Build an Image Classifier

Table of Contents

1. Installation
2. Project Motivation
3. File Descriptions
4. Results
5. Licensing, Authors, and Acknowledgements

Installation

There should be no necessary libraries to run the code here beyond the Anaconda distribution of Python. The code should run with no issues using Python versions 3.*.

Project Motivation

This is a project of Term 1 Udacity Data Science Nanodegree. In this project, I trained an image classifier to recognize different species of flowers.

File Descriptions

• Image Classifier Project.ipynb: showcase work related to this project.
• predict.py: contains code that can be called by a command line application to run prediction on a new image.
• train.py: includes codes to train the classifier that can be called by a command line application.
• cat_to_name.json: is provided by Udacity to load in a mapping from category label to category name.

Results

The image classifier trained through tranfer learning was able to reach 88.6% accuracy on the test data.

Licensing, Authors, Acknowledgements

Credits must be given to Udacity for providing starting code and data for this project. A LICENSE file is also included.