转换模型出现这种bug是为什么

[Jackiemin233]

============Convert Model Args=============
modelPath: ./input/model.pdmodel
paramPath: ./input/model.pdiparams
outputDir: ./Output
enableOptimizeModel: 0
enableLogModelInfo: 0
sliceDataSize:4096
Starting...
You choosed not to optimize model, consequently, optimizing model is skiped.

Converting model...
WARNING: OMP_NUM_THREADS set to 12, not 1. The computation speed will not be optimized if you use data parallel. It will fail if this PaddlePaddle binary is compiled with OpenBlas since OpenBlas does not support multi-threads.
PLEASE USE OMP_NUM_THREADS WISELY.
Organizing model operators info...
Organizing model operators info successfully.
Organizing model variables info...
A fetal error occured. Failed to convert model.
Traceback (most recent call last):
File "convertModel.py", line 554, in main
convertToPaddleJSModel(modelDir, modelName, paramsName, outputDir, useGPUOpt)
File "convertModel.py", line 468, in convertToPaddleJSModel
organizeModelVariableInfo(result)
File "convertModel.py", line 218, in organizeModelVariableInfo
exe.run(program, feed=feedData, fetch_list=fetch_targets, return_numpy=False)
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 1463, in run
six.reraise(*sys.exc_info())
File "/root/miniconda3/lib/python3.8/site-packages/six.py", line 719, in reraise
raise value
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 1450, in run
res = self._run_impl(program=program,
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 1639, in _run_impl
program, new_exe = self._executor_cache.get_program_and_executor(
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 743, in get_program_and_executor
return self._get_cached_program_and_executor(
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 807, in _get_program_and_executor
_apply_inplace_addto_pass(program, enable_inplace, enable_addto,
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/executor.py", line 410, in _apply_inplace_addto_pass
_apply_pass(program, empty_startup_program, pass_name, attrs,
File "/root/miniconda3/lib/python3.8/site-packages/paddle/fluid/framework.py", line 4335, in _apply_pass
attrs = core.apply_pass(
RuntimeError: (NotFound) Operator (sync_batch_norm) is not registered.
[Hint: op_info_ptr should not be null.] (at /paddle/paddle/fluid/framework/op_info.h:156)