Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) AGX Orin DevKit
• DeepStream Version 6.3
• Issue Type( question, bug)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
gst-launch-1.0 -e -v uridecodebin3 uri="file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4" ! nvvideoconvert ! m.sink_0 nvstreammux name=m batch-size=1 width=1280 height=720 ! nvinfer name=nvinfer2 process-mode=primary unique-id=1 batch-size=1 interval=0 config-file-path="/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/config_infer_secondary_carmake.txt" model-engine-file="/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine" ! nvdsosd display-text=1 display-clock=1 ! nvdslogger fps-measurement-interval-sec=1 ! nvvideoconvert ! x264enc tune=zerolatency ! h264parse ! qtmux ! filesink location=test_carmake.mp4
I try to run nvinfer classifier as Primary nvinfer on the whole frame.
However It generates classifier metadata only for some frames where result of a first class is > than some threshold (> 0.51 ?)
I need to get classifier metadata for every frame
classifier-threshold is set to 0, so it should not remove classifier metadata.
I am looking into nvinfer to see where classification metadata is deleted, any help will be appreciated.
Am I missing some other config parameter?
UPD:
forgot to modify config file, with this one it works. I still have a problem with a custom classifier model, I will compare configs and probably return to this question.
[property]
gpu-id=0
net-scale-factor=1
model-file=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/resnet18.caffemodel
proto-file=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/resnet18.prototxt
model-engine-file=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/resnet18.caffemodel_b16_gpu0_int8.engine
int8-calib-file=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/cal_trt.bin
mean-file=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/mean.ppm
labelfile-path=/opt/nvidia/deepstream/deepstream/samples/models/Secondary_CarMake/labels.txt
force-implicit-batch-dim=1
batch-size=16
model-color-format=1
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
process-mode=2
is-classifier=1
output-blob-names=predictions/Softmax
classifier-async-mode=0
classifier-threshold=0.0
input-object-min-width=128
input-object-min-height=128
operate-on-gie-id=1
operate-on-class-ids=0
classifier-type=carmake
#scaling-filter=0
#scaling-compute-hw=0