tensorflow/models · error · ValueError

Padding for kernel size {} not known.

Error message

Padding for kernel size {} not known.

What it means

Error "Padding for kernel size {} not known." thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/layers/nn_layers.py:84

    return filters

  new_filters = make_divisible(value=filters * multiplier,
                               divisor=divisor,
                               min_value=min_depth,
                               round_down_protect=round_down_protect)

  logging.info('round_filter input=%s output=%s', orig_f, new_filters)
  return int(new_filters)


def get_padding_for_kernel_size(kernel_size):
  """Compute padding size given kernel size."""
  if kernel_size == 7:
    return (3, 3)
  elif kernel_size == 3:
    return (1, 1)
  else:
    raise ValueError('Padding for kernel size {} not known.'.format(
        kernel_size))


@tf_keras.utils.register_keras_serializable(package='Vision')
class SqueezeExcitation(tf_keras.layers.Layer):
  """Creates a squeeze and excitation layer."""

  def __init__(self,
               in_filters,
               out_filters,
               se_ratio,
               divisible_by=1,
               use_3d_input=False,
               kernel_initializer='VarianceScaling',
               kernel_regularizer=None,
               bias_regularizer=None,
               activation='relu',
               gating_activation='sigmoid',

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use a kernel size for which padding is implemented (e.g. odd kernel sizes like 3, 5, 7).
2. Extend the padding table for your kernel size or choose a supported size.

When it happens

Trigger: Thrown at official/vision/modeling/layers/nn_layers.py:84 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/46fd49dd7b894395. Report an issue: GitHub.