Home

Awesome

This repository contains my experiments on the Fashion MNIST dataset curated by Zalando Research. The experiments include the standard image classification task. I experimented with different normalization statistics, model ensembling and more. I downloaded the data from Analytics Vidhya's DataHack portal: https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-apparels/ just because the structure of the files were convenient for me to get started.

From the official GitHub repo of Fashion MNIST:

Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits.

Here's an example how the data looks (each class takes three-rows):

Why we made Fashion-MNIST

The original MNIST dataset contains a lot of handwritten digits. Members of the AI/ML/Data Science community love this dataset and use it as a benchmark to validate their algorithms. In fact, MNIST is often the first dataset researchers try. "If it doesn't work on MNIST, it won't work at all", they said. "Well, if it does work on MNIST, it may still fail on others."

To Serious Machine Learning Researchers

Seriously, we are talking about replacing MNIST. Here are some good reasons: