I run a classification sample in the docker nvcr.io/nvidia/deepstream:5.1-21.02-triton, and change the input source number from 30 to12 in the file source30_1080p_dec_infer-resnet_tiled_display_int8.txt. But I get this information, and the output videos of the sink seems too many.:
** WARN: <create_pipeline:1141>: Num of Tiles less than number of sources, readjusting to 53 rows, 2 columns
I only change the input source number from 30 to12 in the file source30_1080p_dec_infer-resnet_tiled_display_int8.txt.
…
[source12]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file:///workspace/deepstream/stream/3.mp4
num-sources=15
gpu-id=0
(0): memtype_device - Memory type Device
(1): memtype_pinned - Memory type Host Pinned
(2): memtype_unified - Memory type Unified
cudadec-memtype=0
There must be some parameters which should to be adjusted accordingly. Which are they? Where are they?
Any help is appreciated.