In this assignment, you will be trying to model and learn an SVM classifier for images, using just the given features.
We provide an extended version of the Assignment 3 image dataset. This dataset has 10,000 instances of a similar set of 25features (compared to the 3,000 instances in Part 1 of Assignment 3), and you are required to train a multiclass SVM model for predicting the labels on a target set of 2,000 instances.
Similar to the previous assignment, you are expected to experiment with hyperparameter tuning, model and feature selection, and cross-validation to get an optimal accuracy score, which will be evaluated on the leaderboard