keras-team/keras · error · ValueError

adaptive_max_pool supports only 1D/2D/3D

Error message

adaptive_max_pool supports only 1D/2D/3D

What it means

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

Source

Thrown at keras/src/backend/numpy/ops/nn.py:598

            inputs, output_size, "average", data_format
        )
    if dims == 3:
        return _adaptive_pool3d_impl(
            inputs, output_size, "average", data_format
        )
    raise ValueError("adaptive_average_pool supports only 1D/2D/3D")


def adaptive_max_pool(inputs, output_size, data_format=None):
    data_format = standardize_data_format(data_format)
    dims = inputs.ndim - 2
    if dims == 1:
        return _adaptive_pool1d_impl(inputs, output_size, "max", data_format)
    if dims == 2:
        return _adaptive_pool2d_impl(inputs, output_size, "max", data_format)
    if dims == 3:
        return _adaptive_pool3d_impl(inputs, output_size, "max", data_format)
    raise ValueError("adaptive_max_pool supports only 1D/2D/3D")


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/numpy/ops/nn.py:598 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/5288de695f5b0cd1. Report an issue: GitHub.