creating multiple deep learning based image classifiers to identify dog breeds and comparing their performances to select the best model. The two goals of the model are to:
-
detect whether the given image by the contestant is of a dog or not (binary classification problem)
-
If the provided image is of a dog, automatically detecting the breed of the dog for faster and more accurate record keeping.
Deep learning model architectures Tested: AlexNet, VGG16, and Resnet18.
Best performing model: AlexNet