ResNet1D-VariableLengthPooling-For-TimeSeries | Variable Length Pooling for time series data

I think there might be some confusion regarding the term test here.

Difference between test and validation data

What the code actually refers to by test is the validation set not the actual test set. The difference is that the validation set is used during training to see how well the model generalizes. Normally people just cut off a part of the training data and use that for validation. To me it seems like your code is using the same data for training and validation but that's just my assumption because I don't know what ./data looks like.

To work in a strictly scientific way, your model should never see actual test data during training, only training and validation. This way we can assess the models actual ability to generalize on unseen data after training.

Reducing learning rate based on validation accuracy

The reason why you use validation data (called test data in your case) to reduce the learning rate is probably because if you did this using the actual training data and training accuracy the model is more likely to overfit. Why? When you are on a plateau of the training accuracy it does not necessarily imply that it's a plateau of the validation accuracy and the other way round. Meaning you could be stepping in a promising direction regarding the validation accuracy (and thus in a direction of parameters that generalize well) and suddenly you reduce or increase the learning rate because there was a plateau (or non) in the training accuracy.