Closed hasantokatlioglu closed 2 years ago
In deepstream-app you need to set the camera parameters according to your usb camera supported formats. The default is camera-width=640
, camera-height=480
and camera-fps-n=30
.
I changed values and I get new error.
ws/DeepStream-Yolo/config_infer_primary_yoloV5.txt sucessfully
Runtime commands: h: Print this help q: Quit
p: Pause
r: Resume
NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source. To go back to the tiled display, right-click anywhere on the window.
** INFO:
** INFO:
Segmentation fault (core dumped)
Which DeepStream version are you using?
6.1
I didn't get this error here. Can you try to debug the error using gdb?
I saw now you are trying to run on docker, change sink type to 1 and try again.
Hello, I am also facing the same issue. My pipeline is: gst-launch-1.0 pylonsrc cam::ExposureTime=20000 cam::Gain=10.3 ! "video/x-raw,width=640,height=480,framerate=10/1,format=GRAY8" ! videoconvert ! nvvideoconvert ! m.sink_0 nvstreammux name=m batch-size=1 width=1024 height=768 ! nvinfer config-file-path=/home/arun/DeepStream-Yolo/config_infer_primary_yoloV5.txt batch-size=1 unique-id=1 ! autovideosink
I get the following error:
arun@arun:~/DeepStream-Yolo$ gst-launch-1.0 pylonsrc cam::ExposureTime=20000 cam::Gain=10.3 ! "video/x-raw,width=640,height=480,framerate=10/1,format=GRAY8" ! videoconvert ! nvvideoconvert ! m.sink_0 nvstreammux name=m batch-size=1 width=1024 height=768 ! nvinfer config-file-path=/home/arun/DeepStream-Yolo/config_infer_primary_yoloV5.txt batch-size=1 unique-id=1 ! autovideosink
Setting pipeline to PAUSED ...
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:13.592017243 13969 0xaaaaecef4030 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/home/arun/DeepStream-Yolo/model_b1_gpu0_fp32.engine
WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1.
INFO: [Implicit Engine Info]: layers num: 4
0 INPUT kFLOAT input 3x640x640
1 OUTPUT kFLOAT boxes 25200x4
2 OUTPUT kFLOAT scores 25200x1
3 OUTPUT kFLOAT classes 25200x1
0:00:13.657445702 13969 0xaaaaecef4030 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /home/arun/DeepStream-Yolo/model_b1_gpu0_fp32.engine
0:00:13.669595896 13969 0xaaaaecef4030 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<nvinfer0> [UID 1]: Load new model:/home/arun/DeepStream-Yolo/config_infer_primary_yoloV5.txt sucessfully
Pipeline is live and does not need PREROLL ...
Setting pipeline to PLAYING ...
New clock: GstSystemClock
ERROR: from element /GstPipeline:pipeline0/GstPylonSrc:pylonsrc0: Internal data stream error.
Additional debug info:
gstbasesrc.c(3072): gst_base_src_loop (): /GstPipeline:pipeline0/GstPylonSrc:pylonsrc0:
streaming stopped, reason not-negotiated (-4)
Execution ended after 0:00:00.307523235
Setting pipeline to NULL ...
Freeing pipeline ...
arun@arun:~/DeepStream-Yolo$
I am using DeepStream 6.1 and Basler Ace2
thanks Kind Regards Arun
@arun-kumark Try
If you are runing in a x86 platform
gst-launch-1.0 pylonsrc cam::ExposureTime=20000 cam::Gain=10.3 ! "video/x-raw,width=640,height=480,framerate=10/1,format=GRAY8" ! videoconvert ! nvvideoconvert ! m.sink_0 nvstreammux name=m batch-size=1 width=1024 height=768 ! nvinfer config-file-path=/home/arun/DeepStream-Yolo/config_infer_primary_yoloV5.txt batch-size=1 unique-id=1 ! nvvideoconvert ! nvdsosd ! nveglglessink sync=0
If you are running in a Jetson platform:
gst-launch-1.0 pylonsrc cam::ExposureTime=20000 cam::Gain=10.3 ! "video/x-raw,width=640,height=480,framerate=10/1,format=GRAY8" ! videoconvert ! nvvideoconvert ! m.sink_0 nvstreammux name=m batch-size=1 width=1024 height=768 ! nvinfer config-file-path=/home/arun/DeepStream-Yolo/config_infer_primary_yoloV5.txt batch-size=1 unique-id=1 ! nvvideoconvert ! nvdsosd ! nvegltransform ! nveglglessink sync=0
Solved with Jetson platform option :+1:
Thanks!
How can I make this as a Python file ? Any reference Marco ?
How can I make this as a Python file ? Any reference Marco ?
Thanks Marco. I am searching for Basler specific pylonsrc code. I have a graph from running pipeline, but my python code stalls. Attaching the graph file for your reference too..
pipeline_PAUSED_READY.pdf thanks Kind Regards Arun
Can you send the log from the terminal?
I convert .engine but I cannot use please help me
my deepstream_app_config.txt is:
my config_infer_primary_yoloV5.txt is:
![b](https://user-images.githubusercontent.com/93164887/170805020-e983c1a2-8754-4ce0-9c2e-5f4260e99c3a.png)
Thank you!