The project implements Siamese Network with Triplet Loss in Keras to learn meaningful image representations in a lower-dimensional space. By training on the MNIST dataset, it creates a powerful architecture and implements Triplet Loss function. The resulting model enables applications like image search, recommendation systems, and image clustering.
mnist-dataset
triplet-loss
neural-network-architectures
siamese-networks
image-representation-learning-mnist-dataset
deep-learning-with-keras
-
Updated
Feb 24, 2024 - Jupyter Notebook