I'm training a multi-inputs and multi-outputs neural network (for example: use a, b, c's value to predict d, e, f's value)
this is my model structure:
model = Sequential()
model.add(Dense(20, input_dim=3, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(3, activation='sigmoid'))
define the optimizer and loss function:
model.compile(loss='mse', optimizer=opt, metrics=['acc'])
model.evaluate(X_test, Y_test)
finally it outputs: [0.003804852021858096, 0.8663883209228516]
i'm wondering what's the meaning of accuracy(0.8663883209228516), how it was calculated? it's R2 or other else...?
