Created by: liushanshan07

• 训练信息    1）单机单卡    2）显存信息，本地K40机器

• 问题描述：

Traceback (most recent call last): File "./train.py", line 296, in main() File "./train.py", line 292, in main train(args, data_reader=data_reader) train(args, data_reader=data_reader) File "./train.py", line 229, in train results = parallel_exe.run(var_names, feed=get_feeder_data(data, place)) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/parallel_executor.py", line 311, in run return_numpy=return_numpy) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/executor.py", line 775, in run six.reraise(*sys.exc_info()) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/executor.py", line 770, in run use_program_cache=use_program_cache) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/executor.py", line 829, in _run_impl return_numpy=return_numpy) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/executor.py", line 669, in _run_parallel tensors = exe.run(fetch_var_names)._move_to_list() paddle.fluid.core_avx.EnforceNotMet:

--堆栈信息 `C++ Call Stacks (More useful to developers):

0 std::string paddle::platform::GetTraceBackString<std::string const&>(std::string const&, char const*, int) 1 paddle::platform::EnforceNotMet::EnforceNotMet(std::string const&, char const*, int) 2 paddle::framework::Tensor::check_memory_size() const 3 paddle::framework::EigenVector<long, 1, long>::Flatten(paddle::framework::Tensor&) 4 void paddle::operators::SumToLoDTensor(paddle::framework::ExecutionContext const&) 5 std::Function_handler<void (paddle::framework::ExecutionContext const&), paddle::framework::OpKernelRegistrarFunctor<paddle::platform::CUDAPlace, false, 3ul, paddle::operators::SumKernel<paddle::platform::CUDADeviceContext, float>, paddle::operators::SumKernel<paddle::platform::CUDADeviceContext, double>, paddle::operators::SumKernel<paddle::platform::CUDADeviceContext, int>, paddle::operators::SumKernel<paddle::platform::CUDADeviceContext, long>, paddle::operators::SumKernel<paddle::platform::CUDADeviceContext, paddle::platform::float16> >::operator()(char const*, char const*, int) const::{lambda(paddle::framework::ExecutionContext const&)#1 (closed)}>::M_invoke(std::Any_data const&, paddle::framework::ExecutionContext const&) 6 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&, paddle::framework::RuntimeContext*) const 7 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&) const 8 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&) 9 paddle::framework::details::ComputationOpHandle::RunImpl() 10 paddle::framework::details::FastThreadedSSAGraphExecutor::RunOpSync(paddle::framework::details::OpHandleBase*) 11 paddle::framework::details::FastThreadedSSAGraphExecutor::RunOp(paddle::framework::details::OpHandleBase*, std::shared_ptr<paddle::framework::BlockingQueue > const&, unsigned long*) 12 std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result, std::__future_base::_Result_base::_Deleter>, void> >::_M_invoke(std::_Any_data const&) 13 std::__future_base::_State_base::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>&, bool&) 14 ThreadPool::ThreadPool(unsigned long)::{lambda()#1 (closed)}::operator()() const

Python Call Stacks (More useful to users):

File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/framework.py", line 2423, in append_op attrs=kwargs.get("attrs", None)) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op return self.main_program.current_block().append_op(*args, **kwargs) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/layers/tensor.py", line 443, in sums attrs={'use_mkldnn': False}) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/evaluator.py", line 277, in init out=self.instance_error) File "/home/vis/liushanshan/chinese/model/ctc_attention/1_base/thirdparty/ctc_attention_model.py", line 251, in ctc_attention_train_net error_evaluator = fluid.evaluator.EditDistance(input=decoded_out, label=casted_label) File "./train.py", line 74, in train images, label, label_in, label_out, args, num_classes, data_shape) File "./train.py", line 292, in main train(args, data_reader=data_reader) File "./train.py", line 296, in main()

Error Message Summary:

PaddleCheckError: holder_ should not be null Tensor holds no memory. Call Tensor::mutable_data first. at [/root/Paddle/paddle/fluid/framework/tensor.cc:23] [operator < sum > error]`