How does keras define "accuracy" and "loss"?

Question

I can't find how Keras defines "accuracy" and "loss". I know I can specify different metrics (e.g. mse, cross entropy) - but keras prints out a standard "accuracy". How is that defined? Likewise for loss: I know I can specify different types of regularization -- are those in the loss?

Ideally, I'd like to print out the equation used to define it; if not, I'll settle for an answer here.

Solution

Have a look at metrics.py, there you can find definition of all available metrics including different types of accuracy. Accuracy is not printed unless you add it to the list of desired metrics when you compile your model.

Regularizers are by definition added to the loss. For example, see add_loss method of the Layerclass.

Update

The type of accuracy is determined based on the objective function, see training.py. The default choice is categorical_accuracy. Other types like binary_accuracy and sparse_categorical_accuracy are selected when the objective function is either binary or sparse.

Comments

[SRobertJames]

If I add to the metrics 'accuracy', which metric is that? There are several in metrics.py that have the word "accuracy" in them?

[SRobertJames]

Thanks. But what is selected if the objective function is neither, but is mse? What does accuracy mean in that context?

[Sergii Gryshkevych]

In such case categorical_accuracy is selected and it means according to the documentation "Calculates the mean accuracy rate across all predictions for multiclass classification problems". If your problem is not classification, then it does not make much sense to include accuracy. @SRobertJames

[Xiaohong Deng]

@SergiiGryshkevych I clicked the link for categorical_accuracy. Seems categorical_accuracy is no longer a scalar. It's an array now if I'm not mistaken. categorical_accuracy