Working with the Fashion-MNIST Dataset
Explore how to use the Fashion-MNIST dataset with Conditional GANs to generate labeled images. Understand dataset specifics, adapt CGAN code, train the model, and evaluate its performance on fashion categories. Gain practical skills in applying GANs to more complex image data.
We'll cover the following...
So, we know by now that the MNIST dataset is comprised of a bunch of handwritten numbers. It is the de facto standard for the machine learning community, and it is often used to validate processes. Another group has decided to create another dataset that could be a better replacement. This project is named Fashion-MNIST and is designed to be a simple drop-in replacement.
Fashion-MNIST consists of a training set of 60,000 images and labels and a test set of 10,000 images and labels. All images are grayscale and set to