Use Keras to train a neural network for the binary classification of muffins and

Use Keras to train a neural network for the binary classification of muffins and Chihuahuas based on images from this dataset. https://www.kaggle.com/datasets/samuelcortinhas/mu…
Images must be transformed from JPG to RGB (or grayscale) pixel values and scaled down. The student is asked to:
experiment with different network architectures (at least 3) and training hyperparameters,
use 5-fold cross validation to compute your risk estimates,
thoroughly discuss the obtained results, documenting the influence of the choice of the network architecture and the tuning of the hyperparameters on the final cross-validated risk estimate.
While the training loss can be chosen freely, the reported cross-validated estimates must be computed according to the zero-one loss. The experimental project is typically based on implementing two or more learning algorithms (or variants of the same algorithm) from scratch. The algorithms are compared on real-world datasets. The programming language is immaterial. However, the implementation should be reasonable in terms of running time and memory footprint. If the experimental project is based on neural networks, then the student is allowed to use a toolbox (e.g., Keras). The report, preferably written using LaTeX, will be evaluated according to the following criteria:
Correctness of the general methodological approach
Reproducibility of the experiments
Correctness of the approach used for choosing the hyperparameters
Clarity of exposition If your solution is adapted from other sources (e.g., Kaggle), this must be clearly stated, and the report should explain the differences and compare the experimental results. Steps to complete the experimental project:Fill out a form to choose a project
Create a public repository containing both the code and the report (in pdf)
Fill out a form to turn in the project