Evaluating data augmentation | AWS Certified AI Practitioner (AIF-C01) original practice question

1.2Standard

Increase image-classification training data.

Do not change the label meaning.

Choose two practices.

Hint 1: Focus on the requirement

Identify what must change and what must remain unchanged. Then choose the command whose scope matches that requirement.

Hint 2: Check each command's role

Separate commands that display information, change state, remove data, or affect a child process.

左右反転や切り抜きが対象ラベルを保つか確認して適用する: Only meaning-preserving transformations are used.
拡張を訓練データへ適用し、検証・テストは独立した実データで評価する: Artificially inflated evaluation is avoided.
ラベルを変える変換も無条件に適用する: Training labels become wrong.
検証画像を拡張して訓練へ混ぜる: Evaluation data leaks.

Detailed explanation

CorrectConfirm that flips or crops preserve the target label before applying them

Only meaning-preserving transformations are used.

CorrectAugment training data and evaluate on independent validation and test data

Artificially inflated evaluation is avoided.

IncorrectApply label-changing transformations without review

Training labels become wrong.

IncorrectMix augmented validation images into training

Evaluation data leaks.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 1.2のデータ拡張、品質、評価分割を確認する。

拡張によるデータ量増加と、ラベル保持・評価独立性を説明できる。

Foundation review

Check whether the command acts on the current shell, a new process, an existing process, or a file.

Use the supplied command and compare the output with the expected result.

Question IDAWS-AIF-273

EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認

Last technical review2026-08-20