Google Professional Machine Learning Engineer
Comments
Loading comments...
Ultimate access to all questions.
You are a Machine Learning Engineer at a startup that wants to deploy an object detection model to identify the presence and location of its logo in images. The startup has provided you with a large, unlabeled dataset of images, some containing the logo and others not. The startup is under budget constraints and requires a solution that balances cost, efficiency, and accuracy. Additionally, the solution must be scalable to accommodate future increases in dataset size. Considering these constraints, what is the most efficient approach to label the data, train, and deploy the model? Choose the best option.
A
Utilize Google Cloud’s Data Labelling Service for automated data labeling and AutoML Object Detection for model training and deployment, leveraging Google Cloud's managed services to reduce manual effort and ensure scalability.
B
Employ the Vision API to detect logos in images for labeling purposes, then use AI Platform to construct and train a convolutional neural network, which may require additional customization for higher accuracy.
C
Organize images manually into two folders based on logo presence and absence, then use AI Platform to develop and train a convolutional neural network, a time-consuming process that may not be scalable.
D
Manually categorize images into two folders (logo present and absent), then leverage AI Platform to create and train a real-time object detection model, which may not be necessary given the startup's current requirements.