What is the difference between Keras model.evaluate() and model.predict()?

It is about regularization. model.predict() returns the final output of the model, i.e. answer. While model.evaluate() returns the loss. The loss is used to train the model (via backpropagation) and it is not the answer.

This video of ML Tokyo should help to understand the difference between model.evaluate() and model.predict().

The model.evaluate function predicts the output for the given input and then computes the metrics function specified in the model.compile and based on y_true and y_pred and returns the computed metric value as the output.

The model.predict just returns back the y_pred

So if you use model.predict and then compute the metrics yourself, the computed metric value should turn out to be the same as model.evaluate

For example, one would use model.predict instead of model.evaluate in evaluating an RNN/ LSTM based models where the output needs to be fed as input in next time step

The problem lies in the fact that every metric in Keras is evaluated in a following manner:

1. For each batch a metric value is evaluated.
2. A current value of loss (after k batches is equal to a mean value of your metric across computed k batches).
3. The final result is obtained as a mean of all losses computed for all batches.

Most of the most popular metrics (like mse, categorical_crossentropy, mae) etc. - as a mean of loss value of each example - have a property that such evaluation ends up with a proper result. But in case of Dice Coefficient - a mean of its value across all of the batches is not equal to actual value computed on a whole dataset and as model.evaluate() uses such way of computations - this is the direct cause of your problem.

The keras.evaluate() function will give you the loss value for every batch. The keras.predict() function will give you the actual predictions for all samples in a batch, for all batches. So even if you use the same data, the differences will be there because the value of a loss function will be almost always different than the predicted values. These are two different things.