In this project I used a created image classifier to identify dog breeds determining which image classification algorithm works the "best" on classifying images as "dogs" or "not dogs".
Time how long each algorithm takes to solve the classification problem.
For this image classification task I used an already trained image classification application using a deep learning model called a convolutional neural network (often abbreviated as CNN).
The test_classifier.py file contains an example program that demonstrates how to use the classifier function.
-
Correctly identify which pet images are of dogs (even if breed is misclassified) and which pet images aren't of dogs.
-
Correctly classify the breed of dog, for the images that are of dogs.
-
Determine which CNN model architecture (ResNet, AlexNet, or VGG), "best" achieve the objectives 1 and 2.
-
Consider the time resources required to best achieve objectives 1 and 2, and determine if an alternative solution would have given a "good enough" result, given the amount of time each of the algorithms take to run.
This project was executed in my Udacity's AI Programming with Python Nanodegree program.