Why you are not using test data instead of validation data to calculate an accuracy? If you are not using test data, why did you divide it at the beginning?

I believe it is because in this stage we are still trying to find the best hyperparameters. Therefore, we can still change the architecture, etc... The test dataset is the final evaluation, when everything is already set and we want to find the final model performance. After evaluating with the test data we "cannot" change anything else.

Follow this topic

Nursultan Toksanbayev

Last answered:

17 Nov 2022

Posted on:

06 Nov 2022

Calculating accuracy by not using test data

in Convolutional Neural Networks with TensorFlow in Python / Primary classification task - Part 3

1 answers ( 0 marked as helpful)

Pedro Veiga

Posted on:

17 Nov 2022

Calculating accuracy by not using test data

Submit an answer

related questions