The objective of this project was to create a Convolutional Neural Network (CNN) that was able to classify an image containing either a cherry, strawberry or tomato. I explored multiple model architectures, optimization, and loss functions, and employed transfer learning techniques to fine-tune the model's parameters, ensuring optimal performance in fruit identification. The final model was trained on 2,892 images and a validation set of 600 images which resulted in a model that achieved an accuracy of 80.77% accuracy within an test set of 900 image.
