Scenario 1: CNN Model with Customized Parameters: In this scenario, a Convolutional Neural Network (CNN) was implemented with five different architectures to find the best-performing model.
Scenario 2: Transfer Learning with Pre-trained Models: In this scenario, transfer learning was applied using pre-trained models VGG16 and VGG19. This approach aimed to leverage pre-trained weights from models that performed well on large datasets like ImageNet. Among the two scenarios, the transfer learning approach using VGG16 and VGG19 (Scenario 2) yielded the best performance, demonstrating the effectiveness of using pre-trained models for image classification tasks, especially with limited data.