报错信息

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
/tmp/ipykernel_168/1390243965.py in <module>
----> 1 u8_data_cpu[0]

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/varbase_patch_methods.py in __getitem__(self, item)
    738         else:
    739             # 2. Call c++ func getitem_index_not_tensor to speedup.
--> 740             return self._getitem_index_not_tensor(item)
    741 
    742     def __setitem__(self, item, value):

RuntimeError: (NotFound) Operator slice does not have kernel for {data_type[uint8_t]; data_layout[Undefined(AnyLayout)]; place[Place(cpu)]; library_type[PLAIN]}.
  [Hint: Expected kernel_iter != kernels.end(), but received kernel_iter == kernels.end().] (at /paddle/paddle/fluid/imperative/prepared_operator.cc:403)
  [operator < slice > error]

复现代码

import paddle
from paddle.fluid import core

u8_data = paddle.empty(shape=[2, 3, 4, 4], dtype=paddle.uint8)

u8_data_gpu = paddle.to_tensor(u8_data, place=core.CUDAPlace(0))
u8_data_cpu = paddle.to_tensor(u8_data, place=core.CPUPlace())

u8_data_cpu[0]
u8_data_gpu[0]