A production image classification model is being prepared.
Separate the process that builds the model from the process that predicts a new image.
Which process is inference?
Inference uses a trained model to produce a prediction for new input; training updates model parameters from data.
Detailed explanation
Computing an output for an unseen input with an existing model is inference.
Computing an output for an unseen input with an existing model is inference.
Updating parameters from data is training.
Updating parameters from data is training.
This is data preparation before model input.
This is data preparation before model input.
Measuring performance is evaluation.
Measuring performance is evaluation.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01ガイドのDomain 1.1で、trainingとinferenceの用語を確認する。Expected result
新しい入力に対するモデルの予測処理を推論として区別できる。Key points
- Training
- Inference
- Evaluation
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.