Short Answer

Why did strong desktop-photo results not predict mobile-upload success?

Question: Answer in one to three sentences using the data shift in the cat-app example.

Sample answer: Phone uploads often had different lighting, angles, and backgrounds than the cleaner images collected from the website. Since the model was trained and checked on the website set, those results did not show how well it would handle the mobile photos users actually sent.

Key points:

  • Phone and website photos came from different data distributions.
  • High performance on the website data did not establish performance on the mobile target set.

Rubric: The answer must explain that the change in photo characteristics created a mismatch between the evaluation data and the real-world mobile data.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI