Model cannot be saved because the forward pass of the model is not defined

Question

I am trying to save a model after training. The code trains the model and then I am trying to save the model.

But at the time of saving the model, I get the following error from the model.save API call:

class SiameseModel(Model):
    """The Siamese Network model with a custom training and testing loops.
    Computes the triplet loss using the three embeddings produced by the
    Siamese Network.
    The triplet loss is defined as:
       L(A, P, N) = max(‖f(A) - f(P)‖² - ‖f(A) - f(N)‖² + margin, 0)
    """

    def __init__(self, siamese_network, margin=0.5):
        super(SiameseModel, self).__init__()
        self.siamese_network = siamese_network
        self.margin = margin
        self.loss_tracker = metrics.Mean(name="loss")

    def call(self, inputs):
        return self.siamese_network(inputs)

    def train_step(self, data):
        # GradientTape is a context manager that records every operation that
        # you do inside. We are using it here to compute the loss so we can get
        # the gradients and apply them using the optimizer specified in
        # `compile()`.
        with tf.GradientTape() as tape:
            loss = self._compute_loss(data)

        # Storing the gradients of the loss function with respect to the
        # weights/parameters.
        gradients = tape.gradient(loss, self.siamese_network.trainable_weights)

        # Applying the gradients on the model using the specified optimizer
        self.optimizer.apply_gradients(
            zip(gradients, self.siamese_network.trainable_weights)
        )

        # Let's update and return the training loss metric.
        self.loss_tracker.update_state(loss)
        return {"loss": self.loss_tracker.result()}

    def test_step(self, data):
        loss = self._compute_loss(data)

        # Let's update and return the loss metric.
        self.loss_tracker.update_state(loss)
        return {"loss": self.loss_tracker.result()}

    def _compute_loss(self, data):
        # The output of the network is a tuple containing the distances
        # between the anchor and the positive example, and the anchor and
        # the negative example.
        ap_distance, an_distance = self.siamese_network(data)

        # Computing the Triplet Loss by subtracting both distances and
        # making sure we don't get a negative value.
        loss = ap_distance - an_distance
        loss = tf.maximum(loss + self.margin, 0.0)
        return loss

    @property
    def metrics(self):
        # We need to list our metrics here so the `reset_states()` can be
        # called automatically.
        return [self.loss_tracker]


"""
## Training
We are now ready to train our model.
"""

siamese_model = SiameseModel(siamese_network)
siamese_model.compile(optimizer=optimizers.Adam(0.0001))
siamese_model.fit(train_dataset, epochs=10, validation_data=val_dataset)

siamese_model.save("./siamese_model.pt")

Complete code could be found here: https://github.com/keras-team/keras-io/blob/master/examples/vision/siamese_network.py#L272

Error details is shown below:

ValueError: Model  cannot be saved either because the input shape is not available or because the forward pass of the model is not defined.To define a forward pass, please override `Model.call()`. To specify an input shape, either call `build(input_shape)` directly, or call the model on actual data using `Model()`, `Model.fit()`, or `Model.predict()`. If you have a custom training step, please make sure to invoke the forward pass in train step through `Model.__call__`, i.e. `model(inputs)`, as opposed to `model.call()`.

Model cannot be saved because the forward pass of the model is not defined

0 Answers