tensorflow/models · error · ValueError

sigma should be a float or a tuple/list of 2 floats

Error message

sigma should be a float or a tuple/list of 2 floats

What it means

Error "sigma should be a float or a tuple/list of 2 floats" thrown in tensorflow/models.

Source

Thrown at official/vision/ops/augment.py:232

      `tf.pad`. For more details, please refer to
      https://www.tensorflow.org/api_docs/python/tf/pad.
    constant_values: A `scalar`, the pad value to use in "CONSTANT" padding
      mode.
    name: A name for this operation (optional).

  Returns:
    2-D, 3-D or 4-D `Tensor` of the same dtype as input.

  Raises:
    ValueError: If `image` is not 2, 3 or 4-dimensional,
      if `padding` is other than "REFLECT", "CONSTANT" or "SYMMETRIC",
      if `filter_shape` is invalid,
      or if `sigma` is invalid.
  """
  with tf.name_scope(name or 'gaussian_filter2d'):
    if isinstance(sigma, (list, tuple)):
      if len(sigma) != 2:
        raise ValueError('sigma should be a float or a tuple/list of 2 floats')
    else:
      sigma = (sigma,) * 2

    if any(s < 0 for s in sigma):
      raise ValueError('sigma should be greater than or equal to 0.')

    image = tf.convert_to_tensor(image, name='image')
    sigma = tf.convert_to_tensor(sigma, name='sigma')

    original_ndims = tf.rank(image)
    image = to_4d(image)

    # Keep the precision if it's float;
    # otherwise, convert to float32 for computing.
    orig_dtype = image.dtype
    if not image.dtype.is_floating:
      image = tf.cast(image, tf.float32)

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Pass sigma as a single float or a tuple/list of 2 floats [low, high].
2. Fix the sigma type in the augmentation config.

When it happens

Trigger: Thrown at official/vision/ops/augment.py:232 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/d53dace4729ca5e7. Report an issue: GitHub.