Deepstream_python_app error

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) agx
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.4
• TensorRT Version 7.13
python3 deepstream_test_3.py file:///home/nvidia/juzheng/video/sample_0.mp4

gstname= audio/x-raw
ERROR: [TRT]: …/rtSafe/cuda/reformat.cu (740) - Cuda Error in NCHWToNCQHW4: 700 (an illegal memory access was encountered)
ERROR: [TRT]: FAILED_EXECUTION: std::exception
ERROR: Failed to enqueue inference batch
ERROR: Infer context enqueue buffer failed, nvinfer error:NVDSINFER_TENSORRT_ERROR
0:00:02.709136999 24964 0x225cf000 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 0 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
Error: gst-stream-error-quark: Failed to queue input batch for inferencing (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1225): gst_nvinfer_input_queue_loop (): /GstPipeline:pipeline0/GstNvInfer:primary-inference
Exiting app

ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.711513008 24964 0x225cf000 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 1 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.714845987 24964 0x225cf000 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 2 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.717344274 24964 0x225cf000 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 3 Number of Objects= 0 Vehicle_count= 0 Person_count= 0

Hi,
App failed at preprocess transform input processing. Did you get this issue with original model or your own model? please specify details more.

I use original model. I didn’t change anything.Just run python3 deepstream_test_3.py file:///home/nvidia/juzheng/video/sample_0.mp4

Can you share the video you used? btw, can you run success with builtin video file?

This is builtin video.
python3 deepstream_test_3.py file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4.

ERROR: [TRT]: …/rtSafe/cuda/caskConvolutionRunner.cpp (373) - Cask Error in checkCaskExecError: 7 (Cask Convolution execution)
ERROR: [TRT]: FAILED_EXECUTION: std::exception
ERROR: Failed to enqueue inference batch
ERROR: Infer context enqueue buffer failed, nvinfer error:NVDSINFER_TENSORRT_ERROR
0:00:02.638837287 8666 0x12a57c00 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 0 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.640860329 8666 0x12a57c00 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Error: gst-stream-error-quark: Failed to queue input batch for inferencing (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1225): gst_nvinfer_input_queue_loop (): /GstPipeline:pipeline0/GstNvInfer:primary-inference
Frame Number= 1 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
Exiting app

ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.645566222 8666 0x12a57c00 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing
Frame Number= 2 Number of Objects= 0 Vehicle_count= 0 Person_count= 0
ERROR: Failed to make stream wait on event, cuda err_no:77, err_str:cudaErrorIllegalAddress
ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER_CUDA_ERROR
0:00:02.647540878 8666 0x12a57c00 WARN nvinfer gstnvinfer.cpp:1225:gst_nvinfer_input_queue_loop: error: Failed to queue input batch for inferencing

I see you are using 5.1, but Jetpack version is 4.4, please confirm. please make sure ds version match Jetpack version. ds 5.1 goes with Jetpack 4.5.1