TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", shape=(3, 3, 3,

使用Flask部署TensorFlow應用到服務器上時，多次重複調用後，出現如下錯誤： 

[2019-08-20 10:50:49,807] ERROR in app: Exception on / [POST]
Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1040, in _run
    subfeed, allow_tensor=True, allow_operation=False)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3339, in as_graph_element
    return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3418, in _as_graph_element_locked
    raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("Placeholder:0", shape=(3, 3, 3, 32), dtype=float32) is not an element of this graph.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\app.py", line 1982, in wsgi_app
    response = self.full_dispatch_request()
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\app.py", line 1614, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\app.py", line 1517, in handle_user_exception
    reraise(exc_type, exc_value, tb)
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\_compat.py", line 33, in reraise
    raise value
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\app.py", line 1612, in full_dispatch_request
    rv = self.dispatch_request()
  File "C:\ProgramData\Anaconda3\lib\site-packages\flask\app.py", line 1598, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "D:/Python/dogcat/service_test.py", line 95, in upload_file
    model = load_model('my_models/Xception-03-0.0553-0.9825-0.0324-0.9900.h5')
  File "D:/Python/dogcat\keras\models.py", line 246, in load_model
    topology.load_weights_from_hdf5_group(f['model_weights'], model.layers)
  File "D:/Python/dogcat\keras\engine\topology.py", line 3189, in load_weights_from_hdf5_group
    K.batch_set_value(weight_value_tuples)
  File "D:/Python/dogcat\keras\backend\tensorflow_backend.py", line 2370, in batch_set_value
    get_session().run(assign_ops, feed_dict=feed_dict)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 877, in run
    run_metadata_ptr)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1043, in _run
    'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("Placeholder:0", shape=(3, 3, 3, 32), dtype=float32) is not an element of this graph.

解決方法

from keras.backend import clear_session

# 銷燬當前TF圖並創建一個新的TF圖，避免舊模型/圖層的混亂。
clear_session()