當前位置: 首頁>>代碼示例>>Python>>正文


Python sanitizer.ClipOption方法代碼示例

本文整理匯總了Python中differential_privacy.dp_sgd.dp_optimizer.sanitizer.ClipOption方法的典型用法代碼示例。如果您正苦於以下問題:Python sanitizer.ClipOption方法的具體用法?Python sanitizer.ClipOption怎麽用?Python sanitizer.ClipOption使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在differential_privacy.dp_sgd.dp_optimizer.sanitizer的用法示例。


在下文中一共展示了sanitizer.ClipOption方法的2個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: ComputeDPPrincipalProjection

# 需要導入模塊: from differential_privacy.dp_sgd.dp_optimizer import sanitizer [as 別名]
# 或者: from differential_privacy.dp_sgd.dp_optimizer.sanitizer import ClipOption [as 別名]
def ComputeDPPrincipalProjection(data, projection_dims,
                                 sanitizer, eps_delta, sigma):
  """Compute differentially private projection.

  Args:
    data: the input data, each row is a data vector.
    projection_dims: the projection dimension.
    sanitizer: the sanitizer used for achieving privacy.
    eps_delta: (eps, delta) pair.
    sigma: if not None, use noise sigma; otherwise compute it using
      eps_delta pair.
  Returns:
    A projection matrix with projection_dims columns.
  """

  eps, delta = eps_delta
  # Normalize each row.
  normalized_data = tf.nn.l2_normalize(data, 1)
  covar = tf.matmul(tf.transpose(normalized_data), normalized_data)
  saved_shape = tf.shape(covar)
  num_examples = tf.slice(tf.shape(data), [0], [1])
  if eps > 0:
    # Since the data is already normalized, there is no need to clip
    # the covariance matrix.
    assert delta > 0
    saned_covar = sanitizer.sanitize(
        tf.reshape(covar, [1, -1]), eps_delta, sigma=sigma,
        option=san.ClipOption(1.0, False), num_examples=num_examples)
    saned_covar = tf.reshape(saned_covar, saved_shape)
    # Symmetrize saned_covar. This also reduces the noise variance.
    saned_covar = 0.5 * (saned_covar + tf.transpose(saned_covar))
  else:
    saned_covar = covar

  # Compute the eigen decomposition of the covariance matrix, and
  # return the top projection_dims eigen vectors, represented as columns of
  # the projection matrix.
  eigvals, eigvecs = tf.self_adjoint_eig(saned_covar)
  _, topk_indices = tf.nn.top_k(eigvals, projection_dims)
  topk_indices = tf.reshape(topk_indices, [projection_dims])
  # Gather and return the corresponding eigenvectors.
  return tf.transpose(tf.gather(tf.transpose(eigvecs), topk_indices)) 
開發者ID:ringringyi,項目名稱:DOTA_models,代碼行數:44,代碼來源:dp_pca.py

示例2: ComputeDPPrincipalProjection

# 需要導入模塊: from differential_privacy.dp_sgd.dp_optimizer import sanitizer [as 別名]
# 或者: from differential_privacy.dp_sgd.dp_optimizer.sanitizer import ClipOption [as 別名]
def ComputeDPPrincipalProjection(data, projection_dims,
                                 sanitizer, eps_delta, sigma):
  """Compute differentially private projection.

  Args:
    data: the input data, each row is a data vector.
    projection_dims: the projection dimension.
    sanitizer: the sanitizer used for acheiving privacy.
    eps_delta: (eps, delta) pair.
    sigma: if not None, use noise sigma; otherwise compute it using
      eps_delta pair.
  Returns:
    A projection matrix with projection_dims columns.
  """

  eps, delta = eps_delta
  # Normalize each row.
  normalized_data = tf.nn.l2_normalize(data, 1)
  covar = tf.matmul(tf.transpose(normalized_data), normalized_data)
  saved_shape = tf.shape(covar)
  num_examples = tf.slice(tf.shape(data), [0], [1])
  if eps > 0:
    # Since the data is already normalized, there is no need to clip
    # the covariance matrix.
    assert delta > 0
    saned_covar = sanitizer.sanitize(
        tf.reshape(covar, [1, -1]), eps_delta, sigma=sigma,
        option=san.ClipOption(1.0, False), num_examples=num_examples)
    saned_covar = tf.reshape(saned_covar, saved_shape)
    # Symmetrize saned_covar. This also reduces the noise variance.
    saned_covar = 0.5 * (saned_covar + tf.transpose(saned_covar))
  else:
    saned_covar = covar

  # Compute the eigen decomposition of the covariance matrix, and
  # return the top projection_dims eigen vectors, represented as columns of
  # the projection matrix.
  eigvals, eigvecs = tf.self_adjoint_eig(saned_covar)
  _, topk_indices = tf.nn.top_k(eigvals, projection_dims)
  topk_indices = tf.reshape(topk_indices, [projection_dims])
  # Gather and return the corresponding eigenvectors.
  return tf.transpose(tf.gather(tf.transpose(eigvecs), topk_indices)) 
開發者ID:coderSkyChen,項目名稱:Action_Recognition_Zoo,代碼行數:44,代碼來源:dp_pca.py


注:本文中的differential_privacy.dp_sgd.dp_optimizer.sanitizer.ClipOption方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。