全连接函数 tf.contrib.layers.fully_connected

tf.contrib.layers.fully_connected(
    inputs,
    num_outputs,
    activation_fn=tf.nn.relu,
    normalizer_fn=None,
    normalizer_params=None,
    weights_initializer=initializers.xavier_initializer(),
    weights_regularizer=None,
    biases_initializer=tf.zeros_initializer(),
    biases_regularizer=None,
    reuse=None,
    variables_collections=None,
    outputs_collections=None,
    trainable=True,
    scope=None
)

增加一个全连接层
自动初始化w和b
激活函数默认为relu函数
输出个数由num_outputs指定
参考：
https://tensorflow.google.cn/api_docs/python/tf/contrib/layers/fully_connected