What does it mean if the validation accuracy is equal to the testing accuracy?

Question

What does it mean if the validation accuracy is equal to the testing accuracy?

AAA

2022年4月15日 10:26

I am training a CNN model for my specific problem. I have divided the dataset into 70% training set, 20% validation set, and 10% test set. The validation accuracy achieved was 95% and the test accuracy achieved was also 95%. What does this mean? Is this mean that the model is not biased ( not biased to the samples in the validation set ) and its hyperparameters have been fine-tuned correctly? Also, do these results confirm the generalization ability of the model ( no overfitting)?

Topic cnn validation accuracy

Category Data Science

YoungSheldon · Accepted Answer · 2022年4月15日 10:26

First of all, make sure you did the split before any kind of pre-processing. Splitting data after pre-processing introduces data leakage.

Second, shuffle the data once again, re-train, validate and test, check if the result persists.

If yes, you are right, the model is not biased to the validation set and hyper-parameters have been fine-tuned correctly.

What does it mean if the validation accuracy is equal to the testing accuracy?

About