Hi, I have downloaded the reference graph on my pc (gpu rtx 2080) and encountered this error while executing the graph. Am i missing something? Any assistance would be much appreciated.
Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 348
nvbufsurface: NvBufSurfaceSysToHWCopy: failed in mem copy
ERROR: nvdsinfer_context_impl.cpp:341 Failed to make stream wait on event, cuda err_no:700, err_str:cudaErrorIllegalAddress
ERROR: nvdsinfer_context_impl.cpp:1619 Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:00.930358892 10315 0x7fa8a800b4a0 WARN nvinfer gstnvinfer.cpp:1324:gst_nvinfer_input_queue_loop:<nvinfer_bin_nvinfer> error: Failed to queue input batch for inferencing
2022-02-18 01:00:46.988 ERROR extensions/nvdsbase/nvds_scheduler.cpp@309: Error from /GstPipeline:NvDsScheduler-Pipeline/GstDsNvInferBin:NvDsInferVideo…5080/nv_ds_infer10…2748/GstNvInfer:nvinfer_bin_nvinfer: Failed to queue input batch for inferencing
2022-02-18 01:00:46.988 ERROR extensions/nvdsbase/nvds_scheduler.cpp@311: Debug info:
gstnvinfer.cpp(1324): gst_nvinfer_input_queue_loop (): /GstPipeline:NvDsScheduler-Pipeline/GstDsNvInferBin:NvDsInferVideo…5080/nv_ds_infer10…2748/GstNvInfer:nvinfer_bin_nvinfer
Source 0: Frame Number = 0 Total objects = 0
Returned, stopping playback
cuCtxCreate failed with error(700) gst_eglglessink_cuda_init
Cuda failure: status=700
Error(-1) in buffer allocation
Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 348
Cuda failure: status=700 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 348
ERROR: nvdsinfer_context_impl.cpp:341 Failed to make stream wait on event, cuda err_no:700, err_str:cudaErrorIllegalAddress
nvbufsurface: NvBufSurfaceSysToHWCopy: failed in mem copy
ERROR: nvdsinfer_context_impl.cpp:1619 Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:00.888039088 5632 0x7f972800b4a0 WARN nvinfer gstnvinfer.cpp:1324:gst_nvinfer_input_queue_loop:<nvinfer_bin_nvinfer> error: Failed to queue input batch for inferencing
/opt/nvidia/graph-composer/execute_graph.sh: line 320: 5632 Segmentation fault (core dumped) ${RUN_PREFIX} ${GXE_PATH} -app “${GRAPH_FILES}” -manifest “${MANIFEST_FILE}”
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) • DeepStream Version • JetPack Version (valid for Jetson only) • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) • Issue Type( questions, new requirements, bugs) • 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) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
• Hardware Platform (Jetson / GPU) dGPU (RTX 2080) • DeepStream Version 6.0 • JetPack Version (valid for Jetson only) • TensorRT Version 8.0.1 • NVIDIA GPU Driver Version (valid for GPU only) 470.63.01 • Issue Type( questions, new requirements, bugs) • 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) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
I run the deepstream-test1 sample just now and this is the error message
Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=1 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 316
Cuda failure: status=700 in cuResData at line 348
Segmentation fault (core dumped)