keras-team/keras · error · ValueError

You are attempting to initialize a variable while in a state

Error message

You are attempting to initialize a variable while in a stateless scope. This is disallowed. Make sure that all variables are initialized before you start using your layer/model objects.

What it means

Error "You are attempting to initialize a variable while in a stateless scope. This is disallowed. Make sure that all variables are initialized before you start using your layer/model objects." thrown in keras-team/keras.

Source

Thrown at keras/src/backend/tensorflow/core.py:61

            self._value = tf.Variable(
                value,
                shape=self._shape,
                dtype=self._dtype,
                trainable=self.trainable,
                name=self.name,
                aggregation=self._map_aggregation(self.aggregation),
                synchronization=self._map_synchronization(self.synchronization),
            )

    def _initialize_with_initializer(self, initializer):
        self._initialize(lambda: initializer(self._shape, dtype=self._dtype))

    def _deferred_initialize(self):
        if self._value is not None:
            raise ValueError(f"Variable {self.path} is already initialized.")

        if in_stateless_scope():
            raise ValueError(
                "You are attempting to initialize a variable "
                "while in a stateless scope. This is disallowed. "
                "Make sure that all variables are initialized "
                "before you start using your layer/model objects."
            )
        with tf.init_scope():
            self._initialize_with_initializer(self._initializer)
            self._initializer = None

    def _direct_assign(self, value):
        self._value.assign(tf.cast(value, self._value.dtype))

    def _convert_to_tensor(self, value, dtype=None):
        return convert_to_tensor(value, dtype=dtype)

    def numpy(self):  # noqa: F811
        return self.value.numpy()

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/tensorflow/core.py:61 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/31b38c84e6ef872f. Report an issue: GitHub.