keras-team/keras · error · ValueError

adaptive_max_pool supports only 1D/2D/3D inputs

Error message

adaptive_max_pool supports only 1D/2D/3D inputs

What it means

Error "adaptive_max_pool supports only 1D/2D/3D inputs" thrown in keras-team/keras.

Source

Thrown at keras/src/backend/jax/nn.py:695

    if dims == 1:
        return _adaptive_average_pool1d(inputs, output_size, data_format)
    if dims == 2:
        return _adaptive_average_pool2d(inputs, output_size, data_format)
    if dims == 3:
        return _adaptive_average_pool3d(inputs, output_size, data_format)
    raise ValueError("adaptive_average_pool supports only 1D/2D/3D inputs")


def adaptive_max_pool(inputs, output_size, data_format=None):
    data_format = backend.standardize_data_format(data_format)
    dims = inputs.ndim - 2
    if dims == 1:
        return _adaptive_max_pool1d(inputs, output_size, data_format)
    if dims == 2:
        return _adaptive_max_pool2d(inputs, output_size, data_format)
    if dims == 3:
        return _adaptive_max_pool3d(inputs, output_size, data_format)
    raise ValueError("adaptive_max_pool supports only 1D/2D/3D inputs")


def _convert_to_lax_conv_dimension_numbers(
    num_spatial_dims,
    data_format="channels_last",
    transpose=False,
):
    """Create a `lax.ConvDimensionNumbers` for the given inputs."""
    num_dims = num_spatial_dims + 2

    if data_format == "channels_last":
        spatial_dims = tuple(range(1, num_dims - 1))
        inputs_dn = (0, num_dims - 1) + spatial_dims
    else:
        spatial_dims = tuple(range(2, num_dims))
        inputs_dn = (0, 1) + spatial_dims

    if transpose:

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/jax/nn.py:695 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/c0ba774bc4ce7199. Report an issue: GitHub.