AWS Certified Machine Learning – Specialty — Question 7

A company is observing low accuracy while training on the default built-in image classification algorithm in Amazon SageMaker. The Data Science team wants to use an Inception neural network architecture instead of a ResNet architecture.
Which of the following will accomplish this? (Choose two.)

Answer options

• A. Customize the built-in image classification algorithm to use Inception and use this for model training.
• B. Create a support case with the SageMaker team to change the default image classification algorithm to Inception.
• C. Bundle a Docker container with TensorFlow Estimator loaded with an Inception network and use this for model training.
• D. Use custom code in Amazon SageMaker with TensorFlow Estimator to load the model with an Inception network, and use this for model training.
• E. Download and apt-get install the inception network code into an Amazon EC2 instance and use this instance as a Jupyter notebook in Amazon SageMaker.

Correct answer: C, D

Explanation

Options C and D are correct because they both involve using TensorFlow Estimator with an Inception network to train a model, which aligns with the team's objective. Option A is incorrect because the built-in algorithm cannot be customized in that manner, while Option B is not viable as it involves requesting a change from AWS rather than implementing a solution. Option E is also incorrect since it suggests using an EC2 instance, which does not directly align with the requirement to use Amazon SageMaker effectively.