Please provide complete information as applicable to your setup.
We are using NvDCF tracker and we wanted to ask if there’s a way to get track objects by using ColorNames and hog features without losing a significant amount of FPS and without increasing the primary inference interval.
**PERF: 39.47 (39.34) 39.47 (39.34) 39.47 (39.34) 39.47 (39.34) 39.26 (39.13) 39.26 (39.13) 39.26 (39.13)
**PERF: 39.42 (39.37) 39.42 (39.37) 39.42 (39.37) 39.42 (39.37) 39.42 (39.27) 39.42 (39.27) 39.42 (39.27)
This is the performance with the tracker with the sample configuration file config_tracker_NvDCF_perf.yml
**PERF: 30.31 (30.10) 30.31 (30.10) 30.31 (30.10) 30.31 (30.10) 30.31 (30.10) 30.31 (30.10) 30.31 (30.10)
**PERF: 28.68 (28.87) 28.68 (28.87) 28.68 (28.87) 28.68 (28.87) 28.68 (28.87) 28.68 (28.87) 28.68 (28.87)
This is the performance by enabling hog useHog = 1 in config_tracker_NvDCF_perf.yml
**PERF: 17.52 (16.83) 17.52 (16.83) 17.52 (16.83) 19.94 (18.99) 19.94 (18.99) 17.52 (16.83) 17.52 (16.83)
**PERF: 17.86 (17.80) 17.86 (17.80) 17.86 (17.80) 17.86 (18.14) 17.86 (18.14) 17.86 (17.80) 17.86 (17.80)
**PERF: 17.72 (17.71) 17.72 (17.71) 17.72 (17.71) 17.72 (17.89) 17.72 (17.89) 17.72 (17.71) 17.72 (17.71)
Is this the expected performance?
Here’s the Deepstream app configuration file.
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[source0]
enable=1
type=3
uri=file://sample_1080p_h264.mp4
num-sources=7
#drop-frame-interval=2
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
[sink0]
#source0 output as filesink
enable=1
type=1
sync=0
source-id=0
[streammux]
gpu-id=0
live-source=0
batch-size=7
batched-push-timeout=33000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
# attach-sys-ts-as-ntp=1
[tracker]
enable=1
tracker-width=256
tracker-height=256
ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
ll-config-file=config_tracker_NvDCF_perf.yml
gpu-id=0
enable-batch-process=1
enable-past-frame=1
display-tracking-id=1
[primary-gie]
enable=1
gpu-id=0
model-engine-file=models/resnet18_trafficcamnet_pruned.etlt_b7_gpu0_int8.engine
labelfile-path=models/labels.txt
batch-size=7
#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
interval=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=models/nvinfer_config.txt
[tests]
file-loop=0
Below you can find some of the setup information:
• Hardware Platform (Jetson / GPU): Jetson Xavier NX
• DeepStream Version: 6.1
• JetPack Version 5.0.1
• Power Mode 8
• NVIDIA GPU Driver Version: cuda 11.4
• Issue Type: question