tensorflow加载模型，访问模型中的Tensor。

 saver = tf.train.import_meta_graph('model/my-model-290.meta')
 saver.restore(sess, tf.train.latest_checkpoint("model/"))
 print sess.run('w:0')

run()参数含义：

w表示图中的操作名称，0表示该操作返回的第一个Tensor.

saver = tf.train.import_meta_graph('my_test_model-1000.meta')
saver.restore(sess,tf.train.latest_checkpoint('./'))

graph = tf.get_default_graph()
w1 = graph.get_tensor_by_name("w1:0")
w2 = graph.get_tensor_by_name("w2:0")

//google的

Your observations on Tensor naming are absolutely correct: the name of a Tensor is the concatenation of

1. the name of the operation that produced it,
2. a colon (:), and
3. the index of that tensor in the outputs of the operation that produced it.