tensorflow_gan/python/eval/classifier_metrics.py [557:597]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    activations1, activations2):
  """Classifier distance for evaluating a generative model from activations.

  Given two Gaussian distribution with means m and m_w and covariance matrices
  C and C_w, this function calcuates

                                |m - m_w|^2

  which captures how different the distributions of real images and generated
  images (or more accurately, their visual features) are. Note that unlike the
  Inception score, this is a true distance and utilizes information about real
  world images.

  Note that when computed using sample means and sample covariance matrices,
  Frechet distance is biased. It is more biased for small sample sizes. (e.g.
  even if the two distributions are the same, for a small sample size, the
  expected Frechet distance is large). It is important to use the same
  sample size to compute frechet classifier distance when comparing two
  generative models.

  In this variant, we only compute the difference between the means of the
  fitted Gaussians. The computation leads to O(n) vs. O(n^2) memory usage, yet
  still retains much of the same information as FID.

  Args:
    activations1: 2D array of activations of size
      [num_images, num_dims] to use to compute Frechet Inception distance.
    activations2: 2D array of activations of size
      [num_images, num_dims] to use to compute Frechet Inception distance.

  Returns:
    The mean-only Frechet Inception distance. A floating-point scalar of the
    same type as the output of the activations.
  """
  activations1.shape.assert_has_rank(2)
  activations2.shape.assert_has_rank(2)

  activations_dtype = activations1.dtype
  if activations_dtype != tf.float64:
    activations1 = tf.cast(activations1, tf.float64)
    activations2 = tf.cast(activations2, tf.float64)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_gan/python/eval/classifier_metrics.py [614:659]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    activations1, activations2):
  """Classifier distance for evaluating a generative model.

  This is based on the Frechet Inception distance, but for an arbitrary
  classifier.

  This technique is described in detail in https://arxiv.org/abs/1706.08500.
  Given two Gaussian distribution with means m and m_w and covariance matrices
  C and C_w, this function calcuates

          |m - m_w|^2 + (sigma + sigma_w - 2(sigma x sigma_w)^(1/2))

  which captures how different the distributions of real images and generated
  images (or more accurately, their visual features) are. Note that unlike the
  Inception score, this is a true distance and utilizes information about real
  world images. In this variant, we compute diagonal-only covariance matrices.
  As a result, instead of computing an expensive matrix square root, we can do
  something much simpler, and has O(n) vs O(n^2) space complexity.

  Note that when computed using sample means and sample covariance matrices,
  Frechet distance is biased. It is more biased for small sample sizes. (e.g.
  even if the two distributions are the same, for a small sample size, the
  expected Frechet distance is large). It is important to use the same
  sample size to compute frechet classifier distance when comparing two
  generative models.

  Args:
    activations1: First activations to use to compute Frechet Inception
      distance.
    activations2: Second activations to use to compute Frechet Inception
      distance.

  Returns:
    The diagonal-only Frechet Inception distance. A floating-point scalar of
    the same type as the output of the activations.

  Raises:
    ValueError: If the shape of the variance and mean vectors are not equal.
  """
  activations1.shape.assert_has_rank(2)
  activations2.shape.assert_has_rank(2)

  activations_dtype = activations1.dtype
  if activations_dtype != tf.float64:
    activations1 = tf.cast(activations1, tf.float64)
    activations2 = tf.cast(activations2, tf.float64)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -