This is my first attempt to CNN in Pytorch. I have gone by few tutorials, but still need some clarification.
I have theoretical question, I don't understand why in early stopping function we base on validation set, not train or test set?
Has it something common with metrics we got from validation set?
The number of training epochs is one of the training hyper-parameters. Therefore, you MUST NOT use the test data to determine the value of this hyper-parameter. Additionally, you cannot use the training set itself to determine the value of early stopping. Therefore, you need to use the validation set for determining this value.
