Like MNIST, Fashion MNIST consists of a training set consisting of 60,000 examples belonging to 10 different classes and a test set of 10,000 examples. Each training example is a gray-scale image, 28x28 in size. The authors of the work further claim that the Fashion MNIST should actually replace MNIST dataset for benchmarking of new Machine Learning or Computer Vision models.
The researchers introduced Fashion-MNIST as a drop in replacement for MNIST dataset. The new dataset contains images of various clothing items - such as shirts, shoes, coats and other fashion items.
Fashion MNIST shares the shame train-test split structure as MNIST. Whereas in the case of MNIST dataset, the class labels were digits 0-9. The class labels for Fashion MNIST are:
In this post we will be trying out different models and compare their results:
List of models:
1.CNN with 3 Convolutional Layers
2.VGG Like Model