@刘看山 您好，请问一下这种情况怎么处理呀
runfile('D:/bs/ocrcn/train_simple.py', wdir='D:/bs/ocrcn')
[autoreload of tensorflow_datasets.core.tf_compat failed: Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\extensions\autoreload.py", line 246, in check
superreload(m, reload, self.old_objects)
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\extensions\autoreload.py", line 369, in superreload
module = reload(module)
File "C:\ProgramData\Anaconda3\lib\imp.py", line 315, in reload
return importlib.reload(module)
File "C:\ProgramData\Anaconda3\lib\importlib_init_.py", line 159, in reload
name=parent_name) from None
ImportError: parent 'tensorflow_datasets.core' not in sys.modules
]
INFO 03.30 21:45:13 train_simple.py:56: all characters: 3755
Traceback (most recent call last):

File "", line 1, in
runfile('D:/bs/ocrcn/train_simple.py', wdir='D:/bs/ocrcn')

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile
execfile(filename, namespace)

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "D:/bs/ocrcn/train_simple.py", line 137, in
train()

File "D:/bs/ocrcn/train_simple.py", line 63, in train
for data in train_dataset.take(2):

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\data\ops\iterator_ops.py", line 622, in next
return self.next()

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\data\ops\iterator_ops.py", line 666, in next
return self._next_internal()

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\data\ops\iterator_ops.py", line 651, in _next_internal
output_shapes=self._flat_output_shapes)

File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\ops\gen_dataset_ops.py", line 2673, in iterator_get_next_sync
_six.raise_from(_core._status_to_exception(e.code, message), None)

File "", line 3, in raise_from

InvalidArgumentError: {{function_node __inference_Dataset_map_parse_example_v2_31}} Input to reshape is a tensor with 4096 values, but the requested shape has 4600
[[{{node Reshape}}]] [Op:IteratorGetNextSync]
最开始还能跑一个batch