Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
DeepStreamSDK 6.0.1
I have a Deepstream Docker running in which I want to process video files with YOLOv4. However, I like the deepstream output to match the input but I don’t know. The video I tested with has a resolution of 3840x2160. I tried to adapt these values in the deepstrea-config file but it crashed the code.
My config file looks like this:
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=1
#gie-kitti-output-dir=/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/labels
[tiled-display]
enable=1
rows=1
columns=1
width=3840
height=2160
gpu-id=0
#(0): nvbuf-mem-default - Default memory allocated, specific to particular platform
#(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory, applicable for Tesla
#(2): nvbuf-mem-cuda-device - Allocate Device cuda memory, applicable for Tesla
#(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory, applicable for Tesla
#(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson
nvbuf-memory-type=3
[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI
type=3
num-sources=1
uri=file://../../streams/IMG_2522.mp4
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
nvbuf-memory-type=3
[streammux]
gpu-id=0
batch-size=1
batched-push-timeout=80000
## Set muxer output width and height
width=3840
height=2160
nvbuf-memory-type=0
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1
sync=0
source-id=0
gpu-id=0
nvbuf-memory-type=3
qos=0
[osd]
enable=0
gpu-id=0
border-width=3
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Arial
nvbuf-memory-type=3
[primary-gie]
enable=1
gpu-id=0
# Modify as necessary
batch-size=1
#Required by the app for OSD, not a plugin property
bbox-border-color0=1;0;0;1
bbox-border-color1=0;1;1;1
bbox-border-color2=0;0;1;1
bbox-border-color3=0;1;0;1
gie-unique-id=1
# Replace the infer primary config file when you need to
# use other detection models
#config-file=config_infer_primary_frcnn.txt
#config-file=config_infer_primary_ssd.txt
#config-file=config_infer_primary_dssd.txt
#config-file=config_infer_primary_retinanet.txt
#config-file=config_infer_primary_yolov3.txt
config-file=config_infer_primary_yolov4_lp.txt
#config-file=config_infer_primary_detectnet_v2.txt
nvbuf-memory-type=3
[sink1]
enable=1
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265 3=mpeg4
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=0
bitrate=2000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
profile=0
output-file=output.mp4
source-id=0
[sink2]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming 5=Overlay
type=1
#1=h264 2=h265
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=0
bitrate=4000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
profile=0
# set below properties in case of RTSPStreaming
rtsp-port=8554
udp-port=5400
[tracker]
enable=1
# For NvDCF and DeepSORT tracker, tracker-width and tracker-height must be a multiple of 32, respectively
tracker-width=640
tracker-height=384
ll-lib-file=/opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_nvmultiobjecttracker.so
# ll-config-file required to set different tracker types
# ll-config-file=../deepstream-app/config_tracker_IOU.yml
# ll-config-file=../deepstream-app/config_tracker_NvDCF_perf.yml
ll-config-file=../deepstream-app/config_tracker_NvDCF_accuracy.yml
# ll-config-file=../deepstream-app/config_tracker_DeepSORT.yml
gpu-id=0
enable-batch-process=1
enable-past-frame=1
display-tracking-id=1
[tests]
file-loop=0
[ds-example]
enable=1
processing-width=1248
processing-height=384
full-frame=0
blur-objects=1
unique-id=15
nvbuf-memory-type=3
So when I change the default value of the width and height of the tilted-display and the streammux to 3840x2160 and the memory type of the streammux to 0 the resolution is correct but the whole image quality is just not like the original. You can even see it in the image size which was 109 MB previously and is now just 9 MB. What is causing this downfall in quality and image size?
Can someone tell me what I’m doing wrong or is this even the right approach?