Answer-first summary for fast verification
Answer: Develop the model training code for image classification, and train a model by using Vertex AI custom training.
The correct answer is D. Given that the images are already cropped to show one of ten specific traffic signs, this problem is more suited to image classification rather than object detection. AutoML options (A and B) do not offer sufficient flexibility for tuning the model during training. Therefore, the best approach is to develop custom training code for image classification and use Vertex AI custom training to train the model, which allows for the necessary tuning.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
As a machine learning engineer, you are tasked with developing a model to identify different traffic signs from a large dataset of images. These images were extracted from dashboard camera videos and then cropped to each show one of ten specific traffic signs. Your dataset consists of 100,000 labeled images stored in a Cloud Storage bucket. Additionally, you need the ability to tune the model during each training run to ensure optimal performance. Given these requirements, how should you approach training the model?
A
Train a model for object detection by using Vertex AI AutoML.
B
Train a model for image classification by using Vertex AI AutoML.
C
Develop the model training code for object detection, and train a model by using Vertex AI custom training.
D
Develop the model training code for image classification, and train a model by using Vertex AI custom training.
No comments yet.