Which Metric Evaluates Correctly Classified Images in a Classification Model?

Model Evaluation Metrics

A company has built an image classification model to predict plant diseases from photos of plant leaves. The company wants to evaluate how many images the model classified correctly. Which evaluation metric should the company use to measure the model's performance?

R-squared score
Accuracy Source Reference Answer
Root mean squared error (RMSE)
Learning rate

Community Votes

100%

100% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

The question tests whether you can distinguish classification metrics from regression metrics; accuracy is correct because it directly measures the percentage of correct predictions out of total predictions.

For a plant disease image classification model, accuracy is the standard metric to measure the proportion of images classified correctly. Community votes unanimously support accuracy over regression metrics like R-squared and RMSE.

Choosing RMSE or R-squared because they are common metrics, but they are for continuous regression problems, not classification tasks like predicting plant disease categories.

Community Discussion (8 comments)

galliaj 👍 5

Accuracy is the most straightforward metric, measuring the proportion of correctly predicted instances out of the total instances. It is suitable when the classes are balanced (but can be misleading for imbalanced datasets).

Rcosmos 👍 1 Selected: B

A métrica de avaliação mais apropriada para medir quantas imagens o modelo classificou corretamente em um modelo de classificação é: B. Exatidão Explicações das opções: A. Pontuação R-quadrado: usada em modelos de regressão, não em classificação. B. Exatidão (Accuracy): mede a proporção de previsões corretas em relação ao total de previsões — ideal para classificação. C. RMSE (Raiz do Erro Quadrático Médio): também usada em regressão, não em problemas de classificação. D. Taxa de aprendizado: não é uma métrica de avaliação, mas um hiperparâmetro usado durante o treinamento do modelo. Resposta correta: B. Exatidão

Rcosmos 👍 1 Selected: B

A exatidão (accuracy) é uma métrica apropriada para avaliar o desempenho de um modelo de classificação de imagens. Ela calcula a proporção de imagens que o modelo classificou corretamente em relação ao total de imagens avaliadas.

Jessiii 👍 1 Selected: B

ccuracy is a straightforward metric that measures the percentage of correct predictions made by the model out of all predictions. Since the goal is to evaluate how many images the model classified correctly (i.e., how many plant diseases were identified correctly from photos), accuracy is the best choice for this classification task.

afrazkhan 👍 1 Selected: B

Its Accuracy as it tells the proportion of the correctly predicted values to the incorrect ones.

Moon 👍 1 Selected: B

B. Accuracy: This metric measures the proportion of correctly classified instances out of the total number of instances. It directly addresses the question of "how many images the model classified correctly."

modatruhio 👍 4

https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html

jove 👍 3 Selected: B

Accuracy for sure

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Expert Analysis

Why the Answer Is Correct

Accuracy is the most direct metric for classification problems because it computes the ratio of correctly predicted labels to the total number of predictions. In this scenario, the company wants to know 'how many images the model classified correctly,' which is exactly what accuracy measures. Commenters noted that accuracy is straightforward and suitable when classes are balanced, and it is the default metric to report for such tasks.

Why the Other Options Are Wrong

R-squared and RMSE are designed for regression tasks where the target is a continuous value, not discrete classes. Learning rate is a hyperparameter that controls how much the model weights are updated during training, not a performance evaluation metric. Therefore, options A, C, and D do not answer the question of measuring classification performance.

Community Comment Notes

All commenters selected accuracy, with several explicitly explaining that it measures the proportion of correct predictions. One comment appended an official AWS documentation link about metrics for classification validation, reinforcing that accuracy is a standard choice for classification models. Another comment in Portuguese also correctly identified accuracy as 'Exatidão' and explained why the other options are regression- or training-related.

Official Reference

Exam Strategy

When asked which metric measures correct classifications, immediately think of accuracy. Eliminate regression metrics and training hyperparameters from consideration, and remember that accuracy is calculated as (correct predictions) / (total predictions).

Related Analysis

Practice All AIF-C01 Questions

Access 100 questions with complete answers and detailed explanations.

View Full AIF-C01 Practice Test →

← Back to AIF-C01 Study Guide