有時我們希望在一個python的文件空間同時載入多個模型，例如 我們建立了10個CNN模型，然后我們又寫了一個預測類Predict，這個類會從已經保存好的模型restore恢復相應的圖結構以及模型參數。然后我們會創建10個Predict的對象Instance，每個Instance負責一個模型的預測。

Predict的核心為：

class Predict: def __init__(self....):  創建sess  創建恢復器tf.train.Saver  從恢復點恢復參數：tf.train.Saver.restore(...) def predict(self,...):  sess.run(output,feed_dict={輸入})

如果我們直接輪流生成10個不同的Predict 對象的話，我們發現tensorflow是會報類似于下面的錯誤：

 File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status))tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [256,512] rhs shape= [640,512]   [[Node: save/Assign_14 = Assign[T=DT_FLOAT, _class=["loc:@fullcont/Variable"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](fullcont/Variable, save/RestoreV2_14)]]During handling of the above exception, another exception occurred:Traceback (most recent call last): File "PREDICT_WITH_SPARK_DATAFLOW_WA.py", line 121, in <module> pre2=Predict(label=new_list[1]) File "PREDICT_WITH_SPARK_DATAFLOW_WA.py", line 47, in __init__ self.saver.restore(self.sess,self.ckpt.model_checkpoint_path) File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1560, in restore {self.saver_def.filename_tensor_name: save_path}) File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 895, in run run_metadata_ptr) File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1124, in _run feed_dict_tensor, options, run_metadata) File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run options, run_metadata) File "/home/jiangminghao/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call raise type(e)(node_def, op, message)tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [256,512] rhs shape= [640,512]

關鍵就是：

Assign requires shapes of both tensors to match.意思是載入模型的時候 賦值失敗。主要是因為不同對象里面的不同sess使用了同一進程空間下的相同的默認圖graph。

正確的解決方法：

class Predict: def __init__(self....):  self.graph=tf.Graph()#為每個類(實例)單獨創建一個graph  with self.graph.as_default():    self.saver=tf.train.import_meta_graph(...)#創建恢復器    #注意！恢復器必須要在新創建的圖里面生成,否則會出錯。  self.sess=tf.Session(graph=self.graph)#創建新的sess  with self.sess.as_default():    with self.graph.as_default():     self.saver.restore(self.sess,...)#從恢復點恢復參數 def predict(self,...):  sess.run(output,feed_dict={輸入})