In this challenge, you will work with the BAA500 pollen dataset. This dataset includes 15 different pollen species, each represented by a collection of segmented pollen grain images (one grain per image).

For this assignment, a reduced subset of the full dataset has been provided, consisting of 24,000 training images, 3,000 validation images, and 3,000 test images, with a resolution of 128 x 128 pixels, grayscale. The sample names have been randomized, ensuring no correspondence with the original BAA500 dataset samples. The training and validation datasets are labelled in .csv files, where each row contains the name of a sample (image) and its label. However, the test dataset does not include labels; to maintain consistency, a .csv file is provided for the test dataset where all samples are labelled as `unknown`.

You must develop your models exclusively using the training and validation datasets. Once your model is ready, you will test it on the test dataset and upload the generated .csv file containing your classifier's predictions for each sample. Your submission will be evaluated in a competitive ranking. A portion of your grade for this assignment will be determined proportionally based on the highest score in the competition.