官方的接口是这样的
tf.nn.dropout(x, keep_prob, noise_shape=None, seed=None, name=None)
根据给出的keep_prob参数,将输入tensor x按比例输出。
默认情况下, 每个元素保存或丢弃都是独立的。后面这段没太懂,以后懂了再补上: If noise_shape is specified, it must be broadcastable to the shape of x, and only dimensions with noise_shape[i] == shape(x)[i] will make independent decisions. For example, if shape(x) = [k, l, m, n] and noise_shape = [k, 1, 1, n], each batch and channel component will be kept independently and each row and column will be kept or not kept together.
x : 输入tensor
keep_prob : float类型,每个元素被保留下来的概率
noise_shape : 一个1维的int32张量,代表了随机产生“保留/丢弃”标志的shape。
seed : 整形变量,随机数种子。
name : 名字,没啥用。