Table of Contents

1. Challenge

   Retrieve the ibean Datasets

   1. Retrieve the training, validation, and testing ibean datasets:

      • ibean Training Data: https://storage.googleapis.com/ibeans/train.zip
      • ibean Validation Data: https://storage.googleapis.com/ibeans/validation.zip
      • ibean Test Data: https://storage.googleapis.com/ibeans/test.zip

   2. Extract the compressed data.

2. Challenge

   Explore the ibean Data

   1. Explore the folder structure created by decompressing the data to understand how to load the images.
   2. Identify the data classes and the file naming convention.
   3. View some of the images from each class to help you understand the data.
3. Challenge

   Load the ibean Data, and Transform It to a Suitable Form for the Model

   1. Review the model expectations to understand how you should load the data.
   2. Load the training, validation, and test datasets into the program.
   3. Label your data according to the expected model output.
4. Challenge

   Build and Train a Model to Classify the Images

   1. Review the model expectations to know how the model should accept and output data.
   2. Create an appropriate neural network model using Keras.
   3. Compile your model with the correct loss function for the problem and label type.
   4. Train your model to reach the desired accuracy. Remember to capture the history!
   5. Save your model.
5. Challenge

   Evaluate Your Model with the Test Data

   1. Generate model statistics on the test data. Ensure you've met or exceeded the desired accuracy.
   2. Plot your model's accuracy and loss for the training process.