tensorflowで複数のグラフを用いる場合にエラーが起きてしまいます．

Question

tensorflowで複数のモデルを切り替えて使いたいと思っているのですが，以下の2つのグラフを切り替えて結果を出す以下のコードを実行したところ，

import tensorflow as tf
import numpy as np

graph1 = tf.Graph()
with graph1.as_default():
    holder = tf.placeholder(tf.int32)
    var = tf.Variable(10)
    ret = holder * var
    
graph2 = tf.Graph()
with graph2.as_default():
    holder = tf.placeholder(tf.int32)
    var = tf.Variable(10)
    ret = holder * var


with tf.Session(graph=graph1) as sess:
    sess.run(tf.global_variables_initializer())
    feed = {holder: 1}
    ret = sess.run(ret,feed_dict = feed)
    print(ret)
with tf.Session(graph=graph2) as sess:
    sess.run(tf.global_variables_initializer())
    feed = {holder: 2}
    ret = sess.run(ret,feed_dict = feed)
    print(ret)

以下のようなエラーが発生して発生してしまいます．これはなぜなのでしょうか？原因を教えてくださると助かります．

Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1064, in _run
allow_operation=False)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3035, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3114, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("Placeholder:0", dtype=int32) is not an element of this graph.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "multi_graph.py", line 20, in <module>
ret = sess.run(ret,feed_dict = feed)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1067, in _run
+ e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", dtype=int32) is not an element of this graph.

Answer 1

Tensorの名前（holder、var、ret）が重複しています。holder1、holder2のように各グラフで分離しましょう。このような場合は名前が重なりやすいので、別々のクラスにした方が良いと思いますが。