Using 2D Convolutional Layers to classify apparels obtaining 90.81% accuracy. The Fashion MNIST training set contains 55,000 images, and the test set contains 10,000 images.
Each image is a 28x28 grayscale image (just like the images in the original MNIST), associated with a label from 10 classes (t-shirts, trousers, pullovers, dresses, coats, sandals, shirts, sneakers, bags, and ankle boots).