Clarifying - test / validation

[dorienh]

Just a little question to clarify validation and test set. Is validation set used? Or is the loss shown during training 'validation loss' in the log, the test set (e/g. it's not used during training, just to keep track). The latter is fine, no validation needed if not used, if it is, all the better :)

[Luckygyana]

Yes we divide the dataset into training and validation and testing set. Testing set is not touched anything in training process. We can optimize the model with validation set.

[dorienh]

Thanks for clarifying, so test set is only evaluated at the very end. Got it!