转载

https://blog.csdn.net/MiniCnCoder/article/details/80007213

tf.get_variable() 域tf.variable()的区别于联系：

前者是对后者加以限制，两次以上的调用会出错。

    with tf.variable_scope('conv1') as scope:
        weights = tf.get_variable('weights',
                                  shape=[3,3,3,16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(images,weights,strides=[1,1,1,1],padding='SAME')
        pre_activation = tf.nn.bias_add(conv,biases)
        conv1 = tf.nn.relu(pre_activation,name=scope.name)

tf.variable_scope() 与tf.name_scpoe():

后者只能管住操作，但是管不住名字。

def trainning(loss,learning_rate):
    with tf.name_scope('optimiezer'):
        optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
        global_step= tf.Variable(0,name='gloabl_step',trainable=False)
        train_op = optimizer.minimize(loss,global_step=global_step)
    return train_op