Hello, I’m encountering issues running DeepStream on a Jetson Nano. Previously, DeepStream was running correctly on the Jetson Nano.
After running sudo apt-get update and sudo apt-get upgrade, I encountered the following error:
sudo deepstream-app -c source2_1080p_dec_infer-resnet_demux_int8.txt
nvbuf_utils: Could not get EGL display connection
nvbuf_utils: ERROR getting proc addr of eglCreateImageKHR
nvbuf_utils: ERROR getting proc addr of eglDestroyImageKHR
nvbufsurftransform: cuInit failed: 100
(Argus) Error EndOfFile: Unexpected error in reading socket (in src/rpc/socket/client/ClientSocketManager.cpp, function recvThreadCore(), line 266)
(Argus) Error EndOfFile: Receive worker failure, notifying 1 waiting threads (in src/rpc/socket/client/ClientSocketManager.cpp, function recvThreadCore(), line 340)
(Argus) Error InvalidState: Argus client is exiting with 1 outstanding client threads (in src/rpc/socket/client/ClientSocketManager.cpp, function recvThreadCore(), line 357)
(Argus) Error EndOfFile: Receiving thread terminated with error (in src/rpc/socket/client/ClientSocketManager.cpp, function recvThreadWrapper(), line 368)
(Argus) Error EndOfFile: Client thread received an error from socket (in src/rpc/socket/client/ClientSocketManager.cpp, function send(), line 145)
(Argus) Error EndOfFile: (propagating from src/rpc/socket/client/SocketClientDispatch.cpp, function dispatch(), line 91)
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
nvbufsurftransform: cuInit failed: 100
Even after reinstalling DeepStream, I’m still encountering the same problem.
Any idea how to solve such a problem ?
Thanks in advance
This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
Please check if you installed the driver properly, you can run sample deviceQuery to check the status, or run ls -l /dev/nvidia* to check whether devices created or not.
ls -l /dev/nvidia*
ls: cannot access '/dev/nvidia*': No such file or directory
/usr/local/cuda/samples/1_Utilities/deviceQuery$ ./deviceQuery
./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
cudaGetDeviceCount returned 100
-> no CUDA-capable device is detected
Result = FAIL
Is there a way i can install the cuda driver without flashing the board ?
Yes, it was installed using SDKManager. My current problem is that I don’t have physical access to the Jetson Nano. Is there a way I can reinstall the CUDA driver manually without the SDK ?
I’m not connected to the same network as the jetson Nano, The jetson is using a proxy server, in order to access i need to provide the port, i cannot ssh to it using terminal without mentionning the port. That’s why i have to include it in the sdk.