Created a Siamese Network and implemented Triplet Loss function using Python and Keras. It involved training the network with the Triplet Loss function to produce Embeddings of different classes from MNIST dataset, and used data generator to prepare the data for training.
shahab-ghafoor/Siamese-Network-with-Triplet-Loss-in-Keras
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.
Jupyter Notebook