Is bug ?deepstream docker image 's app run error:Error Code 1: Cudnn (Could not initialize cudnn, please check cudnn installation.)

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
RTX 3090
• DeepStream Version
DEEP Stream 6
• JetPack Version (valid for Jetson only)

• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
Driver Version: 470.82.01 CUDA Version: 11.4
• Issue Type( questions, new requirements, bugs)
is bug?

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

I get deepstream docker image like this:

docker pull nvcr.io/nvidia/deepstream:6.0-devel

sudo docker run -p 9522:22 --restart=always --name deepstream6dev -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=:0 -v /home/incar/data:/data -v /home/incar/source:/source --gpus all -it nvcr.io/nvidia/deepstream:6.0-devel

and I get a error when run command in docker:

root@0ff4a9a48122:/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app# deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt
libEGL warning: DRI2: failed to authenticate
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:1484 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error
0:00:01.704163315 130 0x7fa48c002270 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed
0:00:01.704219274 130 0x7fa48c002270 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild
0:00:01.704231791 130 0x7fa48c002270 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
ERROR: [TRT]: 1: [executionResources.cpp::setTacticSources::146] Error Code 1: Cudnn (Could not initialize cudnn, please check cudnn installation.)
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:1119 Build engine failed from config file
ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:811 failed to build trt engine.
0:00:03.957923451 130 0x7fa48c002270 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 1]: build engine file failed
0:00:03.958191280 130 0x7fa48c002270 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 1]: build backend context failed
0:00:03.958213570 130 0x7fa48c002270 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 1]: generate backend failed, check config file settings
0:00:03.958253365 130 0x7fa48c002270 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start:<primary_gie> error: Failed to create NvDsInferContext instance
0:00:03.958260502 130 0x7fa48c002270 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start:<primary_gie> error: Config file path: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/config_infer_primary.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
** ERROR: main:658: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Failed to create NvDsInferContext instance
Debug info: gstnvinfer.cpp(841): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/config_infer_primary.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

This is a set up issue. Please make sure the GPU driver and CUDA is correct with your host machine.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#platform-and-os-compatibility

my host machine install cuda_11.4.3_470.82.01_linux.run and cudnn-11.4-linux-x64-v8.2.4.15.tgz and I think is ok for your guide. could it have a independent cuda version and cudnn version for docker container ?

Please make sure NVIDIA driver 470.63.01 or above is installed correctly in your host.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.