pintnet tf_util.dropout

net = tf_util.dropout(net, keep_prob=0.7, is_training=is_training,
                      scope='dp1')

具体实现如下

def dropout(inputs,
            is_training,
            scope,
            keep_prob=0.5,
            noise_shape=None):
  """ Dropout layer.

  Args:
    inputs: tensor
    is_training: boolean tf.Variable
    scope: string
    keep_prob: float in [0,1]
    noise_shape: list of ints

  Returns:
    tensor variable
  """
  with tf.variable_scope(scope) as sc:
    outputs = tf.cond(is_training,
                      lambda: tf.nn.dropout(inputs, keep_prob, noise_shape),
                      lambda: inputs)
    return outputs

从代码可以看出是对tf的api进行了封装

以0.7的概率，随机将inputs中的元素设置为0，其他元素按照1.0 / (1 - rate)的倍率进行缩放，这里是1/0.3.

bool b=true;

类似c语言的int a= b?1:2;

如果b为true则a=1，否则a=2；

此函数为，如果is_training为true那么进行dropout语句，否则原样返回inputs