gmm_ops.py 文件源码

def _define_distance_to_clusters(self, data):
    """Defines the Mahalanobis distance to the assigned Gaussian."""
    # TODO(xavigonzalvo): reuse (input - mean) * cov^-1 * (input -
    # mean) from log probability function.
    self._all_scores = []
    for shard in data:
      all_scores = []
      shard = array_ops.expand_dims(shard, 0)
      for c in xrange(self._num_classes):
        if self._covariance_type == FULL_COVARIANCE:
          cov = self._covs[c, :, :]
        elif self._covariance_type == DIAG_COVARIANCE:
          cov = array_ops.diag(self._covs[c, :])
        inverse = linalg_ops.matrix_inverse(cov + self._min_var)
        inv_cov = array_ops.tile(
            array_ops.expand_dims(inverse, 0),
            array_ops.stack([self._num_examples, 1, 1]))
        diff = array_ops.transpose(shard - self._means[c, :, :], perm=[1, 0, 2])
        m_left = math_ops.matmul(diff, inv_cov)
        all_scores.append(
            math_ops.sqrt(
                math_ops.matmul(
                    m_left, array_ops.transpose(
                        diff, perm=[0, 2, 1]))))
      self._all_scores.append(
          array_ops.reshape(
              array_ops.concat(all_scores, 1),
              array_ops.stack([self._num_examples, self._num_classes])))

    # Distance to the associated class.
    self._all_scores = array_ops.concat(self._all_scores, 0)
    assignments = array_ops.concat(self.assignments(), 0)
    rows = math_ops.to_int64(math_ops.range(0, self._num_examples))
    indices = array_ops.concat(
        [array_ops.expand_dims(rows, 1), array_ops.expand_dims(assignments, 1)],
        1)
    self._scores = array_ops.gather_nd(self._all_scores, indices)