tf2fluid加载转换后的模型时报错
Created by: yanwb
C:\program\Anaconda3\python.exe D:/python/Python_workspace/tf2fluid/result.py
Traceback (most recent call last):
File "D:/python/Python_workspace/tf2fluid/result.py", line 4, in <module>
model = ml.ModelLoader("paddle_model", use_cuda=False)
File "D:\python\Python_workspace\tf2fluid\model_loader.py", line 42, in __init__
fluid.io.load_vars(self.exe, model_dir, vars=var_list)
File "C:\program\Anaconda3\lib\site-packages\paddle\fluid\io.py", line 610, in load_vars
executor.run(load_prog)
File "C:\program\Anaconda3\lib\site-packages\paddle\fluid\executor.py", line 565, in run
use_program_cache=use_program_cache)
File "C:\program\Anaconda3\lib\site-packages\paddle\fluid\executor.py", line 642, in _run
exe.run(program.desc, scope, 0, True, True, fetch_var_name)
paddle.fluid.core.EnforceNotMet: Invoke operator load error.
Python Callstacks:
File "C:\program\Anaconda3\lib\site-packages\paddle\fluid\framework.py", line 1654, in append_op
attrs=kwargs.get("attrs", None))
File "C:\program\Anaconda3\lib\site-packages\paddle\fluid\io.py", line 596, in load_vars
attrs={'file_path': os.path.join(dirname, new_var.name)})
File "D:\python\Python_workspace\tf2fluid\model_loader.py", line 42, in __init__
fluid.io.load_vars(self.exe, model_dir, vars=var_list)
File "D:/python/Python_workspace/tf2fluid/result.py", line 4, in <module>
model = ml.ModelLoader("paddle_model", use_cuda=False)
C++ Callstacks:
Enforce failed. Expected version == 0U, but received version:10 != 0U:0.
Only version 0 is supported at [D:\1.4.1\paddle\paddle\fluid\framework\tensor_util.cc:453]
PaddlePaddle Call Stacks:
Windows not support stack backtrace yet.
Process finished with exit code 1