Segmentation fault` is detected by the operating system
发布时间
阅读量：
阅读量
原因为模型需要输入多个参数，而输入仅有一个参数，或者输入的参数shape不一致
错误原因1：输入数据与模型数据维度不匹配
def run(predictor, input_arg):
# 准备输入
input_names = predictor.get_input_names()
for i, name in enumerate(input_names):
input_tensor = predictor.get_input_handle(name)
# input_tensor.reshape(img[i].shape)
input_tensor.copy_from_cpu(input_arg[i].copy())
错误原因2：paddle lite导出的nb模型模型与当前计算机架构不匹配
比如：导出–valid_targets=arm，运行在x86的机子上
arm架构导出nb模型：
paddle_lite_opt --model_dir=inference_model --optimize_out=YOLOv3_arm --optimize_out_type=naive_buffer --valid_targets=arm
x86架构导出nb模型：
paddle_lite_opt --model_dir=inference_model --optimize_out=YOLOv3_arm --optimize_out_type=naive_buffer --valid_targets=x86
错误信息
--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0 paddle::lite::LightPredictorImpl::Run()
1 paddle::lite::RuntimeProgram::Run()
2 paddle::lite::Instruction::Run()
3 paddle::lite::kernels::host::CastCompute::Run()
----------------------
Error Message Summary:
----------------------
FatalError: `Segmentation fault` is detected by the operating system.
[TimeInfo: *** Aborted at 1650617494 (unix time) try "date -d @1650617494" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x0) received by PID 210350 (TID 0x7f8584bfd740) from PID 0 ***]
Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)
全部评论 (0)
还没有任何评论哟~