Setup Info:
Platform: Jetson Xavier
Deepstream Version: 6.1
Jetpack Version: 5.0.1
TensorRT Version: 8.4.0
Issue Type: question
Hi everyone,
I am trying to get the python sample app rtsp_in_rtsp_out to work on a jetson xavier and ran into a problem with the nvinfer element:
nvinfer gstnvinfer.cpp:943:gst_nvinfer_start:<primary-inference> error: Failed to set buffer pool to active
Error: gst-resource-error-quark: Failed to set buffer pool to active (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(943): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference
I’ve been following the installation instructions to this point.
On top of that I’ve had to comment out model-engine-file in dstest1_pgie_config.txt and give write permissions to /samples/models/Primary_Detector
I ran the app with:
python3 deepstream_test1_rtsp_in_rtsp_out.py -i rtsp://sample_1.mp4 rtsp://sample_2.mp4 rtsp://sample_N.mp4 -g nvinfer
Thanks in advance for your answers
yuweiw
July 29, 2022, 9:38am
3
It seems like your env’s problems. Could you try to use the real rtsp source?
I’ve tried using my own RTSP camera source now and got the same error. What are you referring to by “the real source”?
yuweiw
July 29, 2022, 10:22am
5
Yes, you are right. I mean the camera source instead of “rtsp://sample_N.mp4”. Could you attach more log with the cli below:
GST_DEBUG=3 python3 deepstream_test1_rtsp_in_rtsp_out.py -i rtsp://sample_1.mp4 rtsp://sample_2.mp4 rtsp://sample_N.mp4 -g nvinfer
Using a file as input now:
/opt/nvidia/deepstream/deepstream/sources/deepstream_python_apps/apps/deepstream-rtsp-in-rtsp-out$ GST_DEBUG=3 python3 deepstream_test1_rtsp_in_rtsp_out.py -i rtsp://SampleVideo_1280x720_5mb.mp4 -g nvinfer
Output:
Creating Pipeline
Creating streamux
Creating source_bin 0
Creating source bin
source-bin-00
Creating Pgie
Creating tiler
Creating nvvidconv
Creating nvosd
Creating H264 Encoder
Creating H264 rtppay
Adding elements to Pipeline
*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***
Starting pipeline
Opening in BLOCKING MODE
0:00:00.930908417 4134 0xf406f0 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0x197a870 Failed to determine interlace mode
0:00:00.931058242 4134 0xf406f0 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0x197a870 Failed to determine interlace mode
0:00:00.931148130 4134 0xf406f0 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0x197a870 Failed to determine interlace mode
0:00:00.931389219 4134 0xf406f0 WARN v4l2 gstv4l2object.c:2394:gst_v4l2_object_add_interlace_mode:0x197a870 Failed to determine interlace mode
0:00:00.931621188 4134 0xf406f0 WARN v4l2 gstv4l2object.c:4477:gst_v4l2_object_probe_caps:<encoder:src> Failed to probe pixel aspect ratio with VIDIOC_CROPCAP: Unknown error -1
0:00:01.049464718 4134 0xf406f0 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1161> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
0:00:01.051493270 4134 0xf406f0 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
0:01:11.425521471 4134 0xf406f0 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1946> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine successfully
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
nvbufsurface: Failed to create EGLImage.
0:01:11.572509379 4134 0xf406f0 ERROR nvinferallocator gstnvinfer_allocator.cpp:102:gst_nvinfer_allocator_alloc: Error: Could not map EglImage from NvBufSurface for nvinfer
0:01:11.572608836 4134 0xf406f0 WARN GST_BUFFER gstbuffer.c:948:gst_buffer_new_allocate: failed to allocate 88 bytes
0:01:11.572694533 4134 0xf406f0 WARN bufferpool gstbufferpool.c:305:do_alloc_buffer:<bufferpool0> alloc function failed
0:01:11.572742918 4134 0xf406f0 WARN bufferpool gstbufferpool.c:338:default_start:<bufferpool0> failed to allocate buffer
0:01:11.572797830 4134 0xf406f0 ERROR bufferpool gstbufferpool.c:559:gst_buffer_pool_set_active:<bufferpool0> start failed
0:01:11.572850375 4134 0xf406f0 WARN nvinfer gstnvinfer.cpp:943:gst_nvinfer_start:<primary-inference> error: Failed to set buffer pool to active
0:01:11.578325737 4134 0xf406f0 WARN GST_PADS gstpad.c:1142:gst_pad_set_active:<primary-inference:sink> Failed to activate pad
Error: gst-resource-error-quark: Failed to set buffer pool to active (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(943): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference
yuweiw
July 29, 2022, 10:33am
7
nvbufsurface: Failed to create EGLImage.
It seems that there’s something wrong with your env’s display system. Could you have a check?
I currently use the Xavier over SSH with X11. When the device was set up yesterday the desktop worked on a monitor as well.
In an hour I could use the device directly again with a monitor to see if something is wrong. Is there something else I could do to check what might be wrong with the display system?
Unfortunately I cannot access the Xavier today. Is there anything else I can do to check the display system?
yuweiw
August 1, 2022, 2:21am
10
If so, you need to configure the display system in your x11 device to connect the Xavier device display system. Also You can use some softwares like vncviewer.
I can access the Xavier directly today. On this setup the pipeline works. I might try to fix the x11 setup later but for now I will mark the issue as solved.
Thanks for your help
system
Closed
August 15, 2022, 8:41am
12
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.