The following tools and libraries were used (licenses are provided as needed):

- TensorFlow (https://www.tensorflow.org/) and Keras (https://keras.io/) were both used for developing the model's head, training, and saving the model, and are licensed under the Apache License 2.0 (https://www.apache.org/licenses/LICENSE-2.0)

- MobileNetV2 (https://arxiv.org/abs/1801.04381) architecture by Google was used as the base model, and was released under the Apache License 2.0 (https://www.apache.org/licenses/LICENSE-2.0)

- Gradio (https://www.gradio.app/) was used to build the AI interface, and is licensed under the Apache License 2.0 (https://www.apache.org/licenses/LICENSE-2.0)

- scikit-learn (https://scikit-learn.org/) scikit-learn was used as part of a confusion matrix, and is licensed under the BSD 3-Clause License (https://github.com/scikit-learn/scikit-learn/blob/main/COPYING)

- matplotlib (https://matplotlib.org/) matplotlib was used as part of visualising that confusion matrix, and is licensed under a PSF-based license (https://matplotlib.org/stable/users/project/license.html)