Overview: The goal of this issue is to build a pizza classification model using Convolutional Neural Networks (CNN) that can accurately classify images of pizzas based on their types (e.g., Margherita, Pepperoni, BBQ Chicken, etc.).
Tasks:
Preprocess a dataset of pizza images (e.g., resizing, normalization, data augmentation).
Design a CNN architecture for image classification.
Train the model using the preprocessed dataset.
Evaluate the model's performance using appropriate metrics (accuracy, precision, recall, F1 score).
Save the trained model and provide code for loading and using it for prediction on new pizza images.
Write unit tests for the preprocessing and model inference functions.
Update README with usage instructions and details on how to run the model.
Dataset: You can use a public dataset of pizza images, such as the one from Kaggle or any other relevant source.
Expected Outcome:
A well-trained pizza classification model with accuracy above 85%.
A detailed README explaining the model's architecture, dataset used, and how to use the model.
Overview: The goal of this issue is to build a pizza classification model using Convolutional Neural Networks (CNN) that can accurately classify images of pizzas based on their types (e.g., Margherita, Pepperoni, BBQ Chicken, etc.).
Tasks:
Preprocess a dataset of pizza images (e.g., resizing, normalization, data augmentation). Design a CNN architecture for image classification. Train the model using the preprocessed dataset. Evaluate the model's performance using appropriate metrics (accuracy, precision, recall, F1 score). Save the trained model and provide code for loading and using it for prediction on new pizza images. Write unit tests for the preprocessing and model inference functions. Update README with usage instructions and details on how to run the model. Dataset: You can use a public dataset of pizza images, such as the one from Kaggle or any other relevant source.
Expected Outcome:
A well-trained pizza classification model with accuracy above 85%. A detailed README explaining the model's architecture, dataset used, and how to use the model.