Metric names for the GANs loss in Keras

The answer is right here:

self.critic_model = Model(inputs=[real_img, z_disc],
                        outputs=[valid, fake, validity_interpolated, aux1]) #<- 4 outputs

                                                              #4 model losses + 1 total loss:
self.critic_model.compile(loss=[self.wasserstein_loss,        #loss for output 0
                                self.wasserstein_loss,        #loss for output 1
                                partial_gp_loss,              #loss for output 2
                                'categorical_crossentropy']   #loss for output 3
                          optimizer=optimizer,
                          metrics=['accuracy'],           #replicated, one for each output
                          loss_weights=[1, 1, 5, 1])

Your model clearly has 4 outputs, and you defined one loss per output. Whenever you have multiple losses, Keras will sum a total loss for you, so:

• 'loss' is the total loss (sum of all losses for this model)

The other 4 'model_2_loss' are, in order:

• self.wasserstein_loss, for the first output valid
• self.wasserstein_loss, for the second output fake
• partial_gp_loss, for validity_interpolated
• 'categorical_crossentropy' for aux1

For the metrics, since you defined only one, the system replicated this same metric for each of the model's outputs:

• 'model_2_acc', metric for valid
• 'model_2_acc_1', metric for fake
• 'model_2_acc_2', metric for validity_interpolated
• 'model_2_acc_3', metric for aux1

For better loss names, you should add names to the outputs of the models, to the losses, etc., wherever it's possible to add a name parameter.

Some operations accept names, such as: How can I set the name of my loss operation in Tensorflow?

Losses in newer versions, created as objects, also accept names: https://www.tensorflow.org/api_docs/python/tf/keras/losses/CategoricalCrossentropy

Models accept names, such as:

self.critic_model = Model(inputs=[real_img, z_disc],
                          outputs=[valid, fake, validity_interpolated, aux1], 
                          name='critic_model')

Layers accept names, so you should have a name for the output layer of each model to keep track of things better.

I'm not totally familiar with the new eager mode execution concept, but you might try to add a name also whenever you call a model... not sure whether this is possible.

You have two metrics the loss and the accuracy, keras generate the name of the metrics from layer where the outputs of your model are last defined. The outputs of your model are outputs=[valid, fake, validity_interpolated, aux1] so you have four of them and all are define with the critic model:

 fake, aux1 = self.critic(fake_img)
 valid, aux2 = self.critic(real_img)
 validity_interpolated, aux3 = self.critic(interpolated_img)

so all are named name_of_the_model_name_of_the_loss -> Model_2_loss

This show how to add a name parameter to a layer to change the name given to the metric: Is there a way of renaming the metrics and losses of a Keras model?

edit on comment:

The source code from keras is here: https://github.com/tensorflow/tensorflow/blob/v2.1.0/tensorflow/python/keras/engine/training.py#L81-L2865

as shown in metrics_names function below, the first name is hard coded as 'loss' by default, probably because their is always at least a loss, and then name attribute is added automatically:

     @property
      def metrics_names(self):
        """Returns the model's display labels for all outputs."""

        # This property includes all output names including `loss` and per-output
        # losses for backward compatibility.
        metrics_names = ['loss']
        if self._is_compiled:
          # Add output loss metric names to the metric names list.
          if len(self._training_endpoints) > 1:
            metrics_names.extend([
                e.loss_name()
                for e in self._training_endpoints
                if not e.should_skip_target()
            ])

        # Add all metric names.
        metrics_names += [m.name for m in self.metrics]
        return metrics_names

The method return the self.name attribute of the losses and not a variable name that could be used with to call them

You can also use this simple code to see that metrics_names depend on last definition of models outputs:

input_ =  keras.layers.Input(shape=(8,))
x =  keras.layers.Dense(16)(input_)
output1 = keras.layers.Dense(32)(x)
output2 = keras.layers.Dense(32, name="output2")(x)
model = keras.models.Model(inputs=input_, outputs=[output1, output2])
model.compile(loss=["mse", "mae"], optimizer="adam", metrics={"output2":"accuracy"})
print(model.metrics_names)

>>> ['loss', 'dense_3_loss', 'output2_loss', 'output2_acc']