keras-team/keras · error · ValueError

When using `TextVectorization` to tokenize strings, the inpu

Error message

When using `TextVectorization` to tokenize strings, the input rank must be 1 or the last shape dimension must be 1. Received: inputs.shape={inputs.shape} with rank={inputs.shape.rank}

What it means

Error "When using `TextVectorization` to tokenize strings, the input rank must be 1 or the last shape dimension must be 1. Received: inputs.shape={inputs.shape} with rank={inputs.shape.rank}" thrown in keras-team/keras.

Source

Thrown at keras/src/layers/preprocessing/text_vectorization.py:620

                    "strip_punctuation",
                    "lower_and_strip_punctuation",
                ):
                    inputs = tf.strings.regex_replace(
                        inputs,
                        r'[!"#$%&()\*\+,-\./:;<=>?@\[\\\]^_`{|}~\']',
                        "",
                    )
                if callable(self._standardize):
                    inputs = self._standardize(inputs)

            if self._split is not None:
                # If we are splitting, we validate that the 1st axis is of
                # dimension 1 and so can be squeezed out. We do this here
                # instead of after splitting for performance reasons - it's
                # more expensive to squeeze a ragged tensor.
                if inputs.shape.rank > 1:
                    if inputs.shape[-1] != 1:
                        raise ValueError(
                            "When using `TextVectorization` to tokenize "
                            "strings, the input rank must be 1 or the last "
                            f"shape dimension must be 1. Received: "
                            f"inputs.shape={inputs.shape} with "
                            f"rank={inputs.shape.rank}"
                        )
                    else:
                        inputs = tf.squeeze(inputs, axis=-1)
                if self._split == "whitespace":
                    # This treats multiple whitespaces as one whitespace,
                    # and strips leading and trailing whitespace.
                    inputs = tf.strings.split(inputs)
                elif self._split == "character":
                    inputs = tf.strings.unicode_split(inputs, "UTF-8")
                elif callable(self._split):
                    inputs = self._split(inputs)

            # Note that 'inputs' here can be either ragged or dense depending

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/layers/preprocessing/text_vectorization.py:620 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/b0f5cfdd5128c273. Report an issue: GitHub.