Everything is implemented from scratch using numpy. The purpose of this assignment was to experiment with different properties of a neural network and evaluate its ability to classify different fashion items. We use the Fashion MNIST data set, a data set made by Zalando (European e-commerce company). The data set contains 10 different types of fashion categories and has 70 000 gray scale images in total if you combine the test and training data set.
- Run the neuralnet.py file
- Enter the task you want to run (a, b, c, d, e or f)