PROSAGA码农传奇-深度学习-Tensorflow评估，[暂停]

<div class =“post-text”itemprop =“text”>
  
    问题有点不清楚，但我认为这就是你所追求的：
  
  
    您创建的每个张量或操作都有一个可能的参数
     <code>
 name
 </code>
    。通过为每个张量提供一个名称，您可以使用
    <a href="https://www.tensorflow.org/api_docs/python/tf/Graph#get_tensor_by_name" rel="nofollow noreferrer">
       <code>
 tf.Graph().get_tensor_by_name
 </code>
    </A>
     并传递你想要的输入
     <code>
 feed_dict
 </code>
     在打电话的时候。
  
  
    至于保存结果，您可以使用保存模型的当前状态
    <a href="https://www.tensorflow.org/api_docs/python/tf/train/Saver" rel="nofollow noreferrer">
      tf.train.Saver（）
    </A>
     类。
  
  
    下面是一个模型的简单示例，其中在一个脚本中创建并保存模型，然后加载第二个脚本，同样的模型被加载，并使用它的Tensors访问
    <a href="https://www.tensorflow.org/api_docs/python/tf/Graph#get_tensor_by_name" rel="nofollow noreferrer">
       <code>
 tf.Graph().get_tensor_by_name
 </code>
    </A>
    。
  
  
    的
      save_model.py
    </强>
  
   <pre>
 <code>
 #create model
x = tf.placeholder(tf.float32, shape=[3,3], name="x")
w = tf.Variable(tf.random_normal(dtype=tf.float32, shape=[3,3], mean=0, stddev=0.5), name="w") 
xw = tf.multiply(x,w, name="xw")

# create saver
saver = tf.train.Saver()

# run and save model
x_input = np.ones((3,3))*2 # numpy array of 2s
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    xw_out = sess.run(xw, feed_dict={x: x_input})

# save model including variables to ./tmp
    save_path = saver.save(sess, "./tmp/model.ckpt")
    print("Model saved with w at: \n {}".format(w.eval()))

>>>Model saved with w at: 
>>> [[ 0.07033788 -0.9353725   0.9999725 ]
>>> [-0.2922624  -1.143613   -1.0453095 ]
>>> [ 0.02661585  0.18821386  0.19582961]]

print(xw_out)

>>>[[ 0.14067577 -1.870745    1.999945  ]
>>>[-0.5845248  -2.287226   -2.090619  ]
>>>[ 0.05323171  0.3764277   0.39165923]]

</code>
 </pre>
  
    的
      load_model.py
    </强>
  
   <pre>
 <code>
 # load saved model graph
saver = tf.train.import_meta_graph("./tmp/model.ckpt.meta")

x_input = np.ones((3,3))*2 # numpy array of 2s
with tf.Session() as sess:
    # Restore sesssion from saver
    saver.restore(sess, "./tmp/model.ckpt")
    print("Model restored.")

# Check the values of the variables
    w = sess.run(sess.graph.get_tensor_by_name("w:0"))
    xw = sess.run(sess.graph.get_tensor_by_name("xw:0"), feed_dict={"x:0": x_input})
    print("Output calculated with w loaded from ./tmp at: \n {}".format(w))

>>>INFO:tensorflow:Restoring parameters from ./tmp/model.ckpt
>>>Model restored.
>>>Output calculated with w loaded from ./tmp at: 
>>> [[ 0.07033788 -0.9353725   0.9999725 ]
>>> [-0.2922624  -1.143613   -1.0453095 ]
>>> [ 0.02661585  0.18821386  0.19582961]]

print(xw)
>>>[[ 0.14067577 -1.870745    1.999945  ]
>>>[-0.5845248  -2.287226   -2.090619  ]
>>>[ 0.05323171  0.3764277   0.39165923]]

</code>
 </pre>
  
    注意：“
     <code>
 :0
 </code>
    “跟随操作名称
     <code>
 get_tensor_by_name()
 </code>
     指定它是
    
      第0
    
     您想要的那个操作的张量输出。
  
  
    可以看到这段代码在一组jupyter笔记本中工作
    <a href="https://bitbucket.org/FinleyGibson/save-and-load-tf-model/src/master/" rel="nofollow noreferrer">
      这里
    </A>
    ，还有另一个更简单的实现，因为如果您已经构建了图形。
  
</DIV>