MNIST-Classifier

MNIST is a dataset containing 28 by 28 pixel sized grayscale images. This dataset is large, consisting of 60,000 training images and 10,000 test images. It has two variants: MNIST Handwitten Digits which contains images from 0 - 9, and FASHION MNIST which contains images classified as 0 - T-shit/Top, 1 - Trouser, 2 - Pullover, 3 - Dress, 4 - Coat, 5 - Sandal, 6 - Shirt, 7 - Sneaker, 8 - Bag, and 9 - Ankle boot.

Models we'll be Building

In this repo, we'll be building the last two models:

1. A simple linear model. P resource
2. A simple multi-layer linear model. MLP resources
3. A more complex model that utilizes Convolution Neural Networks.(CNNs) CNNs resources

Tools and Libraries to Install

1. Python. Download

2. Anaconda. A free and open-source distribution of the Python and R programming languages for scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system conda. Download

3. PyTorch. An open source machine learning framework that accelerates the path from research prototyping to production deployment. Get Started

Queries

If you have any question concerning the repo, feel free to post your question on the DCS ML Laikipia group, or DM or Email me [email protected]

By Martin Oywa - Laikipia University Computer Students Association (LUCOSA) Chair and DSC ML Facilitator