In this assignment you will practice putting together a simple image classification pipeline based on the k-Nearest Neighbor or the SVM classifier. The goals of this assignment are as follows:
·Understand the basic Image Classification pipeline and the data-driven approach (train/predict stages).
·Understand the train/val/test splits and the use of validation data for hyperparameter tuning.
·Develop proficiency in writing efficient vectorized code with numpy. ·Implement and apply a k-Nearest Neighbor (kNN) classifier.
·Implement and apply a Multiclass Support Vector Machine (SVM) classifier.
(a) k-Nearest Neighbor classifier [50pts]
The notebook knn.ipynb will walk you through implementing the kNN classifier. Fill the blanks in knn.ipynb and utils\classifiers\k_nearest_neighbor.py.
(b) Training a Support Vector Machine [50pts]
The notebook svm.ipynb will walk you through implementing the SVM classifier. Fill the
blanks in svm.ipynb and utils\classifiers\linear_svm.py.
1
