Project code for Udacity's AI Programming with Python Nanodegree program. In this project, students first develop code for an image classifier built with PyTorch, then convert it into a command line application.
This fork is modified to preserve my (Lars Cremean's) final submission for this project. It probably will not work "out-of-the-box", because the flowers dataset is not included, and in the Udacity workspace this is referenced via a symlink to /data/flowers, rather than downloaded from some public source. The flowers directory was divided into train, valid, and test folders, with each containing numbered folders (from "1" to "102"). The files from the http://www.robots.ox.ac.uk/~vgg/data/flowers/102/index.html dataset were sorted and labeled by the folder in which they reside. The zipped flowers.tar.gz file was 329 MB, so I did not include it due to github's file size limitations.
If you are taking Udacity's course, please do not copy this implementation. You'll learn more by working through the problem yourself. Good luck!