I have a neuronal network trained on some data. My testing loss is less than my training loss. As this question is well answered regarding some points here I ask myself, if a custom metric that is used in keras is also affected during training by dropouts? Because except the loss from my lossfunction, my custom metrics from my testing data are not less than training data. If i have dropout, i understand that my training loss can be higher than the testing loss.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.