tensorflow的assgin方法

官网API是这么说的

This operation outputs a Tensor that holds the new value of 'ref' after the value has been assigned. This makes it easier to chain operations that need to use the reset value.

该操作输出一个tensor。当委派结束后，ref就会有新的值value。就是把value值赋值给ref

使用：

    A = tf.Variable(tf.constant(0.0), dtype=tf.float32)
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        print(sess.run(A))
        print(sess.run(tf.assign(A, 10)))
        print(sess.run(A))

输出：