https://aistudio.baidu.com/aistudio/projectdetail/249005

fork的上面那个项目，当在CPU下运行时发生错误，错误信息如下：

2020-11-26 22:28:59.925334,epoch: 0, iter: 0, lr: 0.00033, 'loss': 11583.886, 'loss_cls': 34.709, 'loss_bbox': 10348.819, 'loss_rpn_cls': 481.958, 'loss_rpn_bbox': 718.399, time: 0.097
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py:779: UserWarning: The following exception is not an EOF exception.
"The following exception is not an EOF exception.")
Traceback (most recent call last):
File "faster-rcnn/train_own_data.py", line 153, in
train()
File "faster-rcnn/train_own_data.py", line 145, in train
train_loop()
File "faster-rcnn/train_own_data.py", line 122, in train_loop
feed=feeder.feed(data),return_numpy=False)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 780, in run
six.reraise(*sys.exc_info())
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/six.py", line 693, in reraise
raise value
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 775, in run
use_program_cache=use_program_cache)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 822, in _run_impl
use_program_cache=use_program_cache)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 899, in _run_program
fetch_var_name)
paddle.fluid.core_avx.EnforceNotMet:

--------------------------------------------
C++ Call Stacks (More useful to developers):
--------------------------------------------
0 std::string paddle::platform::GetTraceBackString(std::string const&, char const*, int)
1 paddle::platform::EnforceNotMet::EnforceNotMet(std::string const&, char const*, int)
2 paddle::framework::OperatorWithKernel::ParseInputDataType(paddle::framework::ExecutionContext const&, std::string const&, paddle::framework::proto::VarType_Type*) const
3 paddle::framework::OperatorWithKernel::IndicateVarDataType(paddle::framework::ExecutionContext const&, std::string const&) const
4 paddle::operators::ConvOp::GetExpectedKernelType(paddle::framework::ExecutionContext const&) const
5 paddle::framework::OperatorWithKernel::ChooseKernel(paddle::framework::RuntimeContext const&, paddle::framework::Scope const&, paddle::platform::Place const&) const
6 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, paddle::platform::Place const&, paddle::framework::RuntimeContext*) const
7 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, paddle::platform::Place const&) const
8 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, paddle::platform::Place const&)
9 paddle::framework::Executor::RunPreparedContext(paddle::framework::ExecutorPrepareContext*, paddle::framework::Scope*, bool, bool, bool)
10 paddle::framework::Executor::Run(paddle::framework::ProgramDesc const&, paddle::framework::Scope*, int, bool, bool, std::vector > const&, bool)

------------------------------------------
Python Call Stacks (More useful to users):
------------------------------------------
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2488, in append_op
attrs=kwargs.get("attrs", None))
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
return self.main_program.current_block().append_op(*args, **kwargs)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 2803, in conv2d
"data_format": data_format,
File "/home/aistudio/faster-rcnn/models/resnet.py", line 71, in conv_affine_layer
name=name + '.conv2d.output.1')
File "/home/aistudio/faster-rcnn/models/resnet.py", line 101, in shortcut
return conv_affine_layer(input, ch_out, 1, stride, 0, None, name=name)
File "/home/aistudio/faster-rcnn/models/resnet.py", line 114, in bottleneck
short = shortcut(input, ch_out * 4, stride, name=name + "_branch1")
File "/home/aistudio/faster-rcnn/models/resnet.py", line 125, in layer_warp
res_out = block_func(input, ch_out, stride, name=name + "a")
File "/home/aistudio/faster-rcnn/models/resnet.py", line 180, in add_ResNet_roi_conv5_head
res5 = layer_warp(bottleneck, pool, 512, 3, 2, name="res5")
File "/home/aistudio/faster-rcnn/models/model_builder.py", line 241, in fast_rcnn_heads
self.res5_2_sum = self.add_roi_box_head_func(roi_input, pool_rois)
File "/home/aistudio/faster-rcnn/models/model_builder.py", line 43, in build_model
self.fast_rcnn_heads(self.body_conv)
File "faster-rcnn/train_own_data.py", line 49, in train
model.build_model(image_shape)
File "faster-rcnn/train_own_data.py", line 153, in
train()

----------------------
Error Message Summary:
----------------------
Error: The Tensor in the conv2d Op's Input Variable Input(roi_align_0.tmp_0) is not initialized.
[Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] at (/paddle/paddle/fluid/framework/operator.cc:1144)
[operator < conv2d > error]