预测出core

[Angus07]

错误信息如下：

terminate called after throwing an instance of 'paddle::platform::EnforceNotMet'
what():

---

C++ Call Stacks (More useful to developers):

0 std::string paddle::platform::GetTraceBackString<std::string const&>(std::string const&, char const*, int)
1 paddle::memory::detail::MetadataCache::load(paddle::memory::detail::MemoryBlock const*) const
2 paddle::memory::detail::MemoryBlock::total_size(paddle::memory::detail::MetadataCache const&) const
3 paddle::memory::detail::MemoryBlock::split(paddle::memory::detail::MetadataCache*, unsigned long)
4 paddle::memory::detail::BuddyAllocator::SplitToAlloc(std::_Rb_tree_const_iterator<std::tuple<unsigned long, unsigned long, void*> >, unsigned long)
5 paddle::memory::detail::BuddyAllocator::Alloc(unsigned long)
6 void* paddle::memory::legacy::Allocpaddle::platform::CPUPlace(paddle::platform::CPUPlace const&, unsigned long)
7 paddle::memory::allocation::NaiveBestFitAllocator::AllocateImpl(unsigned long)
8 paddle::memory::allocation::AllocatorFacade::Alloc(boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace> const&, unsigned long)
9 paddle::memory::allocation::AllocatorFacade::AllocShared(boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace> const&, unsigned long)
10 paddle::memory::AllocShared(boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace> const&, unsigned long)
11 paddle::framework::Tensor::mutable_data(boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace>, paddle::framework::proto::VarType_Type, unsigned long)
12 paddle::AnalysisPredictor::SetFeed(std::vector<paddle::PaddleTensor, std::allocatorpaddle::PaddleTensor > const&, paddle::framework::Scope*)
13 paddle::AnalysisPredictor::Run(std::vector<paddle::PaddleTensor, std::allocatorpaddle::PaddleTensor > const&, std::vector<paddle::PaddleTensor, std::allocatorpaddle::PaddleTensor >*, int)

---

Error Message Summary:

PaddleCheckError: Expected desc->check_guards() == true, but received desc->check_guards():0 != true:1.
at [baidu/paddlepaddle/paddle/paddle/fluid/memory/detail/meta_cache.cc:33]

Aborted (core dumped)

core在
#18 0x00007f4a98ffb620 in paddle::AnalysisPredictor::Run(std::vector<paddle::PaddleTensor, std::allocatorpaddle::PaddleTensor > const&, std::vector<paddle::PaddleTensor, std::allocatorpaddle::PaddleTensor >*, int) () from libernie-inference.so

[Shixiaowei02]

您好，这个错误是指针访问非法了，请检查一下业务代码的指针是否有问题。

[LihangLiu]

同碰到这个问题，模型加载没问题，预测run的时候崩了。具体情况是
在预测前创建paddle::PaddleTensor的时候，tensor.data.Resize(size * sizeof(float))中size=500运行正常，size=10000的时候崩了。其他代码和环境一样。
请问是paddle inference的时候，对于tensor的大小有限制么？

[Shixiaowei02]

同碰到这个问题，模型加载没问题，预测run的时候崩了。具体情况是
在预测前创建paddle::PaddleTensor的时候，tensor.data.Resize(size * sizeof(float))中size=500运行正常，size=10000的时候崩了。其他代码和环境一样。
请问是paddle inference的时候，对于tensor的大小有限制么？

没有限制。只要出现
PaddleCheckError: Expected desc->check_guards() == true, but received desc->check_guards():0 != true:1. at [baidu/paddlepaddle/paddle/paddle/fluid/memory/detail/meta_cache.cc:33]
这种报错，就需考虑用户代码内存越界。

[LihangLiu]

好的，我查一下，感谢！

[paddle-bot-old]

Since you haven't replied for more than a year, we have closed this issue/pr.
If the problem is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up.
由于您超过一年未回复，我们将关闭这个issue/pr。
若问题未解决或有后续问题，请随时重新打开，我们会继续跟进。