作者你好，我现在训练出了NER模型，但是在用terminal_predict.py进行预测的时候，模型无法导入，报错如下：
Traceback (most recent call last):
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call
return fn(*args)
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1350, in _run_fn
target_list, run_metadata)
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [768,8] rhs shape= [768,9]
[[{{node save/Assign_200}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Soft\Python\lib\contextlib.py", line 130, in exit
self.gen.throw(type, value, traceback)
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\framework\ops.py", line 5480, in get_controller
yield g
File "F:/fffan/DeepLearning/BERT-BiLSTM-CRF-NER-master/terminal_predict.py", line 65, in
saver.restore(sess, save_path=model_path)
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\training\saver.py", line 1326, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [768,8] rhs shape= [768,9]
[[node save/Assign_200 (defined at D:\Soft\Python\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
作者你好，我现在训练出了NER模型，但是在用terminal_predict.py进行预测的时候，模型无法导入，报错如下： Traceback (most recent call last): File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call return fn(*args) File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1350, in _run_fn target_list, run_metadata) File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\client\session.py", line 1443, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [768,8] rhs shape= [768,9] [[{{node save/Assign_200}}]] During handling of the above exception, another exception occurred: Traceback (most recent call last): File "D:\Soft\Python\lib\contextlib.py", line 130, in exit self.gen.throw(type, value, traceback) File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\framework\ops.py", line 5480, in get_controller yield g File "F:/fffan/DeepLearning/BERT-BiLSTM-CRF-NER-master/terminal_predict.py", line 65, in
saver.restore(sess, save_path=model_path)
File "D:\Soft\Python\lib\site-packages\tensorflow_core\python\training\saver.py", line 1326, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [768,8] rhs shape= [768,9] [[node save/Assign_200 (defined at D:\Soft\Python\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
请问这个是什么情况？