Measure an image-classification model's performance.
Using the same images for training and evaluation would not show performance on unseen inputs.
Why should evaluation data be separated?
Data not used for training help measure how well the model generalizes to unseen inputs.
Detailed explanation
A held-out set shows whether the model works beyond the examples used to fit it.
Data splitting is an evaluation design choice, not a network feature.
Evaluation needs reference labels; splitting does not create them.
The split ratio depends on the project; halving storage is not the purpose.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドのDomain 1.3で訓練・検証・テストの役割を確認する。
Official references
What to confirm
訓練データの再現ではなく、未知データへの性能を測る目的を説明できる。
Key points
- Generalization
- Data split
- Overfitting
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Train-test separation
The test set must not guide parameter fitting or repeated tuning if it is to remain an independent measure.
Distribution match
Held-out data should represent the cases and conditions the deployed model is expected to face.