This is my implementation of an image classifier as per requirements of the second project in the Data Science Nanodegree. The project consists of two parts: a Jupyter Notebook, and a console application implemented as .py scripts.
For the first part, you can examine the results of training a new classifier
on the VGG-13 model by opening Image Classifier Project.html. You can
run this code by opening Image Classifier Project.ipynb.
The file is set up to be run using the run all cells command.
In order to train a classifier based on a different model, change the variable model_name.
For the second part, you can check the functionality by running the following commands:
To see how to train the model, run python train.py -h
To see how to predict using a checkpoint, run python predict.py -h
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.