tensorflow_quantum/python/layers/high_level/noisy_pqc.py [244:289]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._append_layer = elementary.AddCircuit()

        # Set additional parameter controls.
        self.initializer = tf.keras.initializers.get(initializer)
        self.regularizer = tf.keras.regularizers.get(regularizer)
        self.constraint = tf.keras.constraints.get(constraint)

        # Weight creation is not placed in a Build function because the number
        # of weights is independent of the input shape.
        self.parameters = self.add_weight('parameters',
                                          shape=self._symbols.shape,
                                          initializer=self.initializer,
                                          regularizer=self.regularizer,
                                          constraint=self.constraint,
                                          dtype=tf.float32,
                                          trainable=True)

    @property
    def symbols(self):
        """The symbols that are managed by this layer (in-order).

        Note: `symbols[i]` indicates what symbol name the managed variables in
            this layer map to.
        """
        return [sympy.Symbol(x) for x in self._symbols_list]

    def symbol_values(self):
        """Returns a Python `dict` containing symbol name, value pairs.

        Returns:
            Python `dict` with `str` keys and `float` values representing
                the current symbol values.
        """
        return dict(zip(self.symbols, self.get_weights()[0]))

    def build(self, input_shape):
        """Keras build function."""
        super().build(input_shape)

    def call(self, inputs):
        """Keras call function."""
        circuit_batch_dim = tf.gather(tf.shape(inputs), 0)
        tiled_up_model = tf.tile(self._model_circuit, [circuit_batch_dim])
        model_appended = self._append_layer(inputs, append=tiled_up_model)
        tiled_up_parameters = tf.tile([self.parameters], [circuit_batch_dim, 1])
        tiled_up_operators = tf.tile(self._operators, [circuit_batch_dim, 1])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_quantum/python/layers/high_level/pqc.py [256:301]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._append_layer = elementary.AddCircuit()

        # Set additional parameter controls.
        self.initializer = tf.keras.initializers.get(initializer)
        self.regularizer = tf.keras.regularizers.get(regularizer)
        self.constraint = tf.keras.constraints.get(constraint)

        # Weight creation is not placed in a Build function because the number
        # of weights is independent of the input shape.
        self.parameters = self.add_weight('parameters',
                                          shape=self._symbols.shape,
                                          initializer=self.initializer,
                                          regularizer=self.regularizer,
                                          constraint=self.constraint,
                                          dtype=tf.float32,
                                          trainable=True)

    @property
    def symbols(self):
        """The symbols that are managed by this layer (in-order).

        Note: `symbols[i]` indicates what symbol name the managed variables in
            this layer map to.
        """
        return [sympy.Symbol(x) for x in self._symbols_list]

    def symbol_values(self):
        """Returns a Python `dict` containing symbol name, value pairs.

        Returns:
            Python `dict` with `str` keys and `float` values representing
                the current symbol values.
        """
        return dict(zip(self.symbols, self.get_weights()[0]))

    def build(self, input_shape):
        """Keras build function."""
        super().build(input_shape)

    def call(self, inputs):
        """Keras call function."""
        circuit_batch_dim = tf.gather(tf.shape(inputs), 0)
        tiled_up_model = tf.tile(self._model_circuit, [circuit_batch_dim])
        model_appended = self._append_layer(inputs, append=tiled_up_model)
        tiled_up_parameters = tf.tile([self.parameters], [circuit_batch_dim, 1])
        tiled_up_operators = tf.tile(self._operators, [circuit_batch_dim, 1])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -