persistent internal error with multi-image classification in Vertex AI AutoML

[aakose]

Hi, I’m facing an internal error when training an AutoML Vision (multiclass classification) model.
Product: Vertex AI AutoML Vision
Region: asia-northeast1
Dataset: 10+ classes, about 200 images per class
Error: Internal Error occurred. Please try again later.

What I’ve tried: Changed region, Re-created dataset, Verified image formats and class labels Confirmed class balance The error still persists. Since I cannot access internal logs, could you suggest possible solutions or next steps to resolve this issue? Thank you.

[nikacalupas]

Hi aakose,

Welcome to the Google Cloud Community!

The ‘INTERNAL error’ you’ve encountered usually occurs due to transient issues. Here are some suggestions that might help your issue:

• Check the Google Cloud Status Dashboard if there are any current issues or outages affecting Vertex AI or AutoML Vision in the asia-northeast1 region, as Google Cloud posts status updates that could help explain the error.
• Although you’ve already tried, it’s worth waiting a few hours or even a day and retrying, as transient internal errors often fix themselves, especially if they happen occasionally.
• Check for potential image corruption. Open each image and visually inspect it. Corrupted images can cause training failures.

Additionally, you may check this documentation for troubleshooting AutoML models.

If you continue to run into issues, consider reaching out to Google Cloud Support to further check underlying issues. When you contact them, be sure to provide as much detail as possible and include screenshots. This will help them understand your problem better and get it sorted out more quickly.

Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.