Python layers.layer_norm方法代碼示例

本文整理匯總了Python中tensorflow.contrib.layers.python.layers.layer_norm方法的典型用法代碼示例。如果您正苦於以下問題：Python layers.layer_norm方法的具體用法？Python layers.layer_norm怎麽用？Python layers.layer_norm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類tensorflow.contrib.layers.python.layers的用法示例。

在下文中一共展示了layers.layer_norm方法的7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: normalize

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def normalize(inp, activation, reuse, scope):
    """The function to forward the normalization.
    Args:
      inp: the input feature maps.
      reuse: whether reuse the variables for the batch norm.
      scope: the label for this conv layer.
      activation: the activation function for this conv layer.
    Return:
      The processed feature maps.
    """
    if FLAGS.norm == 'batch_norm':
        return tf_layers.batch_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'layer_norm':
        return tf_layers.layer_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'None':
        if activation is not None:
            return activation(inp)        
        return inp
    else:
        raise ValueError('Please set correct normalization.')

## Loss functions

開發者ID:yaoyao-liu，項目名稱:meta-transfer-learning，代碼行數:24，代碼來源:misc.py

示例2: init

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def __init__(self, num_units, forget_bias=1.0, reuse_norm=False,
               input_size=None, activation=nn_ops.relu,
               layer_norm=True, norm_gain=1.0, norm_shift=0.0,
               loop_steps=1, decay_rate=0.9, learning_rate=0.5,
               dropout_keep_prob=1.0, dropout_prob_seed=None):

    if input_size is not None:
      logging.warn("%s: The input_size parameter is deprecated.", self)

    self._num_units = num_units
    self._activation = activation
    self._forget_bias = forget_bias
    self._reuse_norm = reuse_norm
    self._keep_prob = dropout_keep_prob
    self._seed = dropout_prob_seed
    self._layer_norm = layer_norm
    self._S = loop_steps
    self._eta = learning_rate
    self._lambda = decay_rate
    self._g = norm_gain
    self._b = norm_shift

開發者ID:jxwufan，項目名稱:AssociativeRetrieval，代碼行數:23，代碼來源:FastWeightsRNN.py

示例3: normalize

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def normalize(inp, activation, reuse, scope):
    if FLAGS.norm == 'batch_norm':
        return tf_layers.batch_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'layer_norm':
        return tf_layers.layer_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'None':
        if activation is not None:
            return activation(inp)
        else:
            return inp


# Loss functions

開發者ID:kylehkhsu，項目名稱:cactus-maml，代碼行數:15，代碼來源:utils.py

示例4: normalize

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def normalize(inp, activation, reuse, scope):
    if FLAGS.norm == 'batch_norm':
        return tf_layers.batch_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'layer_norm':
        return tf_layers.layer_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'None':
        if activation is not None:
            return activation(inp)
        else:
            return inp

## Loss functions

開發者ID:cbfinn，項目名稱:maml，代碼行數:14，代碼來源:utils.py

示例5: normalize

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def normalize(inp, activation, reuse, scope):
    if FLAGS.norm == 'batch_norm':
        return tf_layers.batch_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'layer_norm':
        return tf_layers.layer_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'None':
        return activation(inp)

## Loss functions

開發者ID:yoonholee，項目名稱:MT-net，代碼行數:11，代碼來源:utils.py

示例6: _norm

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def _norm(self, inp, scope=None):
    reuse = tf.get_variable_scope().reuse
    with vs.variable_scope(scope or "Norm") as scope:
      normalized = layer_norm(inp, reuse=reuse, scope=scope)
      return normalized

開發者ID:jxwufan，項目名稱:AssociativeRetrieval，代碼行數:7，代碼來源:FastWeightsRNN.py

示例7: normalize

# 需要導入模塊: from tensorflow.contrib.layers.python import layers [as 別名]
# 或者: from tensorflow.contrib.layers.python.layers import layer_norm [as 別名]
def normalize(inp, activation, reuse, scope):
    if FLAGS.norm == 'batch_norm':
        return tf_layers.batch_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'layer_norm':
        return tf_layers.layer_norm(inp, activation_fn=activation, reuse=reuse, scope=scope)
    elif FLAGS.norm == 'None':
        if activation is not None:
            return activation(inp)
        else:
            return inp


## Loss functions

開發者ID:xinzheli1217，項目名稱:learning-to-self-train，代碼行數:15，代碼來源:misc.py

注：本文中的tensorflow.contrib.layers.python.layers.layer_norm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。