AWS Certified Machine Learning – Specialty — Question 39

A Machine Learning Specialist is training a model to identify the make and model of vehicles in images. The Specialist wants to use transfer learning and an existing model trained on images of general objects. The Specialist collated a large custom dataset of pictures containing different vehicle makes and models.
What should the Specialist do to initialize the model to re-train it with the custom data?

Answer options

• A. Initialize the model with random weights in all layers including the last fully connected layer.
• B. Initialize the model with pre-trained weights in all layers and replace the last fully connected layer.
• C. Initialize the model with random weights in all layers and replace the last fully connected layer.
• D. Initialize the model with pre-trained weights in all layers including the last fully connected layer.

Correct answer: B

Explanation

The correct answer is B because initializing the model with pre-trained weights allows the Specialist to leverage learned features from the general object dataset, which can enhance performance on the custom vehicle dataset. Replacing the last fully connected layer is necessary to adapt the model to the specific task of vehicle identification, as it requires different output classes than those used in the original training. The other options either do not utilize pre-trained weights effectively or fail to replace the last layer appropriately for this task.