predict时出错

[lijinjiang001]

您好，我在预测时运行predict.py提示出错，能指导一下是什么原因吗，谢谢
Traceback (most recent call last):
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 1139, in _do_call
return fn(*args)
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 1117, in _run_fn
self._extend_graph()
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 1166, in _extend_graph
self._session, graph_def.SerializeToString(), status)
File "D:\Anaconda\lib\contextlib.py", line 88, in exit
next(self.gen)
File "D:\Anaconda\lib\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: Multiple OpKernel registrations match NodeDef 'decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)': 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }' and 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }'
[[Node: decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:/pycharm/code/seq2seq_chatbot_new-master/seq2seq_chatbot_new-master/predict.py", line 43, in
model.saver.restore(sess, ckpt.model_checkpoint_path)
File "D:\Anaconda\lib\site-packages\tensorflow\python\training\saver.py", line 1548, in restore
{self.saver_def.filename_tensor_name: save_path})
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 789, in run
run_metadata_ptr)
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "D:\Anaconda\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Multiple OpKernel registrations match NodeDef 'decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)': 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }' and 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }'
[[Node: decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)]]

Caused by op 'decoder/decoder/GatherTree', defined at:
File "D:/pycharm/code/seq2seq_chatbot_new-master/seq2seq_chatbot_new-master/predict.py", line 39, in
mode='decode', use_attention=True, beam_search=True, beam_size=5, max_gradient_norm=5.0)
File "D:\pycharm\code\seq2seq_chatbot_new-master\seq2seq_chatbot_new-master\model.py", line 21, in init
self.build_model()
File "D:\pycharm\code\seq2seq_chatbot_new-master\seq2seq_chatbot_new-master\model.py", line 148, in build_model
maximum_iterations=10)
File "D:\Anaconda\lib\site-packages\tensorflow\contrib\seq2seq\python\ops\decoder.py", line 296, in dynamic_decode
final_outputs, final_state, final_sequence_lengths)
File "D:\Anaconda\lib\site-packages\tensorflow\contrib\seq2seq\python\ops\beam_search_decoder.py", line 280, in finalize
sequence_length=sequence_lengths)
File "D:\Anaconda\lib\site-packages\tensorflow\contrib\seq2seq\ops\gen_beam_search_ops.py", line 43, in gather_tree
sequence_length=sequence_length, name=name)
File "D:\Anaconda\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op
op_def=op_def)
File "D:\Anaconda\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "D:\Anaconda\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in init
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Multiple OpKernel registrations match NodeDef 'decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)': 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }' and 'op: "GatherTree" device_type: "CPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } }'
[[Node: decoder/decoder/GatherTree = GatherTree[T=DT_INT32](decoder/decoder/TensorArrayStack_1/TensorArrayGatherV3, decoder/decoder/TensorArrayStack_2/TensorArrayGatherV3, decoder/decoder/while/Exit_16)]]

[charlesXu86]

我也是遇到了这样的问题