在运行ai_tooltrain的模型转换样例时遇到的问题

环境：

docker镜像:openexplorer/ai_toolchain_ubuntu_gpu_xj3:v2.0.4

OE包:Open_Explorer_gcc_9.3.0/2.2.3/horizon_xj3_open_explorer_v2.2.3_20220617.tar.gz

宿主机CUDA：11.7 NVIDIA DRIVER：515.65.01

Nvidia-docker版本： 20.10.17

问题类型:其他

按照帖子https://developer.horizon.ai/forumDetail/107952931390742029复现，在运行 ${挂载目录}/ddk/samples/ai_toolchain/horizon_model_convert_sample/04_detection/02_yolov3_darknet53/mappe\01_check.sh是出现了问题

ERROR [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running HzCalibration node. Name:'layer97-conv_weight_HzCalibration' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device

软件无做自定义修改