I'm currently implementing a convolutional neural network model that outputs binary classification (true or false), and the labels are all either 0 or 1. When using the "sigmoid" activation function for the final dense layer, I was wondering whether to set from_logits to true or false in the "binary_crossentropy" loss and the AUC keras metric. I.E. does the sigmoid activation function output logits?
The accuracy with either seems somewhat similar, although it is different, I'm wondering which is most accurate to the parameters of the model. I'm using ResNet50 at the moment.
