PaddleOCR
PaddleOCR copied to clipboard
cuda11.4环境,分类模型报错,报错:[operator < hard_swish > error]
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment:
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
- 运行指令/Command Code:
- 完整报错/Complete Error Message:C++ Traceback (most recent call last):
0 paddle::AnalysisPredictor::ZeroCopyRun()
1 paddle::framework::NaiveExecutor::Run()
2 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, phi::Place const&)
3 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, phi::Place const&) const
4 void phi::HardSwishKernel<float, phi::GPUContext>(phi::GPUContext const&, phi::DenseTensor const&, float, float, float, phi::DenseTensor*)
5 void phi::funcs::ElementwiseKernel<float, phi::funcs::CudaHardSwishFunctor
Error Message Summary:
PreconditionNotMetError: Tensor's dimension is out of bound.Tensor's dimension must be equal or less than the size of its memory.But received Tensor's dimension is d73728 memory's size is 256. [Hint: Expected numel() * SizeOf(dtype()) <= memory_size(), but received numel() * SizeOf(dtype()):73728 > memory_size():256.]
[operator < hard_swish > error]