Welcome! This is the final Project for the Udacity AI with Python Nanodegree.
The Code is written in Python 3.7.7 .
The easiest way to get Python and Jupyter notebook on your machine is my installing the free open-source distribution Anaconda: https://www.anaconda.com/
This project uses the following libraries: Numpy, Pandas, MatplotLib, Pytorch, PIL and json.
If these don't come preinstalled with your Anaconda distribution, you can easily install them from the Anaconda terminal: conda install numpy pandas matplotlib pil
In order to intall Pytorch head over to the Pytorch site select your specs and follow the instructions given. https://pytorch.org/
You can clone this repository using
git clone https://github.com/ebaung/Udacity-AI-Programming-with-Python-Final-Project
Json file
In order for the network to correctly identify the name of the flower a .json file is required. This .json file sorts the data based on numbered folders in the dataset, and those numbers will correspond to specific names specified in the .json file.
Flowers Dataset
Unfortunately, the flower images dataset used for this application is too large to upload to Github. However, you may use any dataset of .jpg images (images of anything, not just flowers!), meeting the following guidelines: -the data need to comprised of 3 folders, training, validation and testing. -the distribution should generally be: 70% training, 10% validation and 20% testing. -these folders should contain numbered subfolders. Each unique number corresponds to a specific category, clarified in the json file (please view the cat_to_name.json file included in this Github repository to see the format).
THE COMMAND LINE APPLICATION: The command line application (Part 2 of this Project) is located in another repository: https://github.com/ebaung/Udacity-AI-Programming-with-Python-Final-Project-Part2
Eugene Baung