This project was completed as part of a semester assignment for my Machine Learning course during my bachelor's degree. I used Python and Jupyter Notebook to implement the assignment, along with libraries such as NumPy, Pandas, Matplotlib, scikit-learn, and Pickle.
The dataset is divided into training and test batches. The test batch includes exactly 1,000 randomly selected images from each class, while the training batches contain the remaining images in random order. Because of this randomness, some training batches may include more samples from certain classes than others. Altogether, the training set contains exactly 5,000 images per class.