keras-team/keras · error · ValueError

adaptive_average_pool supports only 1D/2D/3D

Error message

adaptive_average_pool supports only 1D/2D/3D

What it means

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

Source

Thrown at keras/src/backend/numpy/nn.py:585

    return out


def adaptive_average_pool(inputs, output_size, data_format=None):
    data_format = backend.standardize_data_format(data_format)
    dims = inputs.ndim - 2
    if dims == 1:
        return _adaptive_pool1d_impl(
            inputs, output_size, "average", data_format
        )
    if dims == 2:
        return _adaptive_pool2d_impl(
            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 = backend.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,

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/backend/numpy/nn.py:585 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/83943c1c2f1a0b0f. Report an issue: GitHub.