Deepstrem 5.0 - nvstreammux0 can't handle caps video/x-raw(memory:NVMM), format=(string)RGBA

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

• Jetson
• DeepStream Version 5 release
• JetPack Version 4.4 GA
• TensorRT Version 7.1.3.0

nvstreammux0 can’t handle caps video/x-raw(memory:NVMM), format=(string)RGBA

but, gst-inspect-1.0 report:

SINK template: ‘sink_%u’
Availability: On request
Capabilities:
video/x-raw(memory:NVMM)
format: { (string)NV12, (string)RGBA }
width: [ 1, 2147483647 ]
height: [ 1, 2147483647 ]
framerate: [ 0/1, 2147483647/1 ]
video/x-raw
format: { (string)NV12, (string)RGBA }
width: [ 1, 2147483647 ]
height: [ 1, 2147483647 ]
framerate: [ 0/1, 2147483647/1 ]

this is my pipeline:

gst-launch-1.0 nvarguscamerasrc wbmode=5
! ‘video/x-raw(memory:NVMM), width=(int)1920, height=(int)1080, framerate=30/1, format=(string)NV12’
! nvvideoconvert
! ‘video/x-raw(memory:NVMM), format=(string)RGBA’
! nvstreammux batch-size=1 width=1920 height=1080
! nvinfer config-file-path=./samples/configs/deepstream-app/config_infer_primary.txt batch-size=1 unique-id=1
! nvtracker ll-lib-file=/opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_mot_klt.so
! nvinfer config-file-path=./samples/configs/deepstream-app/config_infer_secondary_carcolor.txt batch-size=16 unique-id=2 infer-on-gie-id=1 infer-on-class-ids=0
! nvmultistreamtiler rows=1 columns=1 width=1280 height=720
! nvvideoconvert ! nvdsosd ! nvegltransform
! nveglglessink

1 Like
3

It has nothing to do with RGBA format.
Have you noticed the “SINK template: ‘sink_%u’” information in the gst-inspect-1.0 result? nvstreammux sink pads are dynamic pads(ghost pads). It can not be specified by format because all sink pads can support “RGBA” format. You need to specify the pad explicitly. For example, replace “nvstreammux batch-size=1 width=1920 height=1080” in your pipeline with “m.sink_0 nvstreammux name=m batch-size=1 width=1920 height=1080”.

Please refer to Pads and capabilities to get more information about dynamic pad

1 Like