G-Streamer based TFLite application on RB5
Join Date: 26 May 16
Posts: 1
Posted: Mon, 2023-07-24 02:41
Hi All,
I'm new to the QTI RB5 applications space and trying to run the sample G-Streamer pipeline from the link https://github.com/quic/sample-apps-for-robotics-platforms/tree/master/R....
I've used the command line as below to use the USB web-camera
gst-launch-1.0 v4l2src device=/dev/video2 ! video/x-raw, format=YUY2, width=1920, height=1080 ! videoconvert ! video/x-raw, format=NV12,wideth=1920,height=1080 ! queue ! tee name=split ! queue ! qtimetamux name=metamux ! queue ! qtioverlay ! queue ! waylandsink sync=false fullscreen=true split. ! queue ! qtimlvconverter ! queue ! qtimltflite delegate=hexagon model=/data/samples/temp/mobilenet_quant_v1_224.tflite ! queue ! qtimlvclassification threshold=60.0 results=3 module=mobilenet labels=/data/samples/temp/labels_short.txt ! text/x-raw ! queue ! metamux.
The pipeline is not executing and is running into the error as below.
** (gst-launch-1.0:3916): CRITICAL **: 07:04:06.557: gst_ml_module_configure: assertion 'gst_ml_parse_labels (input, &list)' failed
ERROR: from element /GstPipeline:pipeline0/GstMLVideoClassification:mlvideoclassification0: GStreamer encountered a general resource error.
Additional debug info:
/data/build-qti-distro-ubuntu-fullstack-debug/tmp-glibc/work/aarch64-oe-linux/gstreamer1.0-plugins-qti-oss-mlvclassification/1.0-r0/gst-plugin-mlvclassification/mlvclassification.c(857): gst_ml_video_classification_set_caps (): /GstPipeline:pipeline0/GstMLVideoClassification:mlvideoclassification0:
Failed to set module options!
From the message, it looks like there is some issues with parsing the lables.txt file. Any suggestions would be greatly appreciate. Thank you so much in advance.
Thanks and regards,
Sachi
Hi,
I'm also facing the same problem. Can anyone suggest anything?