keras-team/keras · error · ValueError

axis size must be divisible by 2. Received: x.shape={x.shape

Error message

axis size must be divisible by 2. Received: x.shape={x.shape} with axis={axis}

What it means

Error "axis size must be divisible by 2. Received: x.shape={x.shape} with axis={axis}" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/tensorflow/nn.py:145

    return tf.nn.selu(x)


def gelu(x, approximate=True):
    x = convert_to_tensor(x)
    return tf.nn.gelu(x, approximate=approximate)


def celu(x, alpha=1.0):
    return tf.maximum(x, 0.0) + alpha * tf.math.expm1(
        tf.minimum(x, 0.0) / alpha
    )


def glu(x, axis=-1):
    x = convert_to_tensor(x)
    canonicalize_axis(axis, len(x.shape))
    if x.shape[axis] % 2 != 0:
        raise ValueError(
            "axis size must be divisible by 2. "
            f"Received: x.shape={x.shape} with axis={axis}"
        )
    x1, x2 = tf.split(x, num_or_size_splits=2, axis=axis)
    return x1 * tf.sigmoid(x2)


def hard_tanh(x):
    return tf.clip_by_value(x, clip_value_min=-1.0, clip_value_max=1.0)


def hard_shrink(x, threshold=0.5):
    return tf.where(tf.abs(x) > threshold, x, tf.zeros_like(x))


def threshold(x, threshold, default_value):
    return tf.where(x > threshold, x, default_value)

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/tensorflow/nn.py:145 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/da83a0665f133a71. Report an issue: GitHub.