tensorflow/models · error · ValueError

sigma should be greater than or equal to 0.

Error message

sigma should be greater than or equal to 0.

What it means

Error "sigma should be greater than or equal to 0." thrown in tensorflow/models.

Source

Thrown at official/vision/ops/augment.py:237

  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)

    channels = tf.shape(image)[3]
    filter_shape = _normalize_tuple(filter_shape, 2, 'filter_shape')

    sigma = tf.cast(sigma, image.dtype)
    gaussian_kernel_x = _get_gaussian_kernel(sigma[1], filter_shape[1])

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Set sigma to a value >= 0.
2. Clip or absolutize the sigma value in the augmentation config.

When it happens

Trigger: Thrown at official/vision/ops/augment.py:237 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/27b5833162f1de3e. Report an issue: GitHub.