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
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Related
Do Not Randomly Mix Sources When Building Validation and Test Sets
Use a Small Amount of Target-Distribution Data in Training with Auxiliary Data
When to Reduce the Influence of Extra Training Data
Training-Development Set
Comparing Errors Across Two Data Sources
Training–Dev Distribution Gap
Domain adaptation solves only certain distribution-shift problems
Choosing Development and Test Data for a Specific Application
Factory Photos and Inspection Tablet Images as a Distribution Mismatch Example
Random Train/Test Splits Can Be Misleading When Deployment Data Differs
Which data should define the dev and test sets for the plant-disease app?
Development and test examples should be drawn to match the kind of data the deployed system is expected to see.
Development and test sets should match the kind of data you expect later.
Match each data group for the plant-disease app with its role.
Order the dataset choices when training data and evaluation data come from different sources.
Why training data and evaluation data may come from different sources
Find the evaluation-set mismatch in a voice-command detector.
Why did strong desktop-photo results not predict mobile-upload success?
Choosing Training and Evaluation Data from Two Image Sources
If training uses extra web-sourced photos, the dev and test sets must also contain web-sourced photos.