Build a classifier from a small set of specialist images.
Reuse representations learned from general images.
Choose two practices.
Reuse a pretrained representation but validate domain distribution, labels, performance, and licensing before applying it.
Detailed explanation
Useful features can reduce data needs.
Useful features can reduce data needs.
Transfer assumptions are verified.
Transfer assumptions are verified.
Distribution and label differences matter.
Distribution and label differences matter.
Rights and usage conditions are ignored.
Rights and usage conditions are ignored.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 1.1の転移学習とモデル利用条件を確認する。Expected result
既存モデルの再利用と対象ドメインの評価を両立できる。Key points
- Transfer learning
- Domain shift
- License
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.