Compare Classifiers for STL10

This sample demonstrates how to train and compare multiple classifiers in Azure ML service for STL 10 dataset. The dataset contains 10 classes: airplane, bird, car, cat, deer, dog, horse, monkey, ship, truck. It contains 500 images of 96*96 for each of the 10 classes, taking total count to 5,000 images. Among all the classifiers used to train the model, CNN with two hidden layers is found to be having most accuracy.