Please provide complete information as applicable to your setup.
Hi Nvs,
I am using deepstream:6.2-level container with RTX 2080Ti dGPU. I am working in the reference app with this code.
Can I know how to modify the pipeline to process every third frame from the input stream, effectively skipping two frames between each processed frame.
Thanks for reply!
My understand of interval is I set interval = 1 means every two frames infer one frame. Does My understand correct?
Another question for multi-model in pipeline, for example, this reference pipeline is peopleNet → tracker → bodypose,below is official peopleNet config file
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
tlt-model-key=tlt_encode
tlt-encoded-model=../models/PeopleNet/resnet34_peoplenet_pruned.etlt
#onnx-file=../models/PeopleNet/resnet34_peoplenet_int8.onnx
#int8-calib-file=../models/PeopleNet/resnet34_peoplenet_int8.txt
labelfile-path=../models/PeopleNet/labels.txt
model-engine-file=../models/PeopleNet/resnet34_peoplenet_int8.onnx_b1_gpu0_int8.engine
uff-input-blob-name=input_1
infer-dims=3;544;960
output-blob-names=output_bbox/BiasAdd;output_cov/Sigmoid
batch-size=1
process-mode=1
model-color-format=0
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=3
cluster-mode=2
interval=0
gie-unique-id=1
## Use the config params below for NMS clustering mode
[class-attrs-all]
topk=8
nms-iou-threshold=0.5
pre-cluster-threshold=0.2
## Per class configurations
[class-attrs-0]
topk=20
nms-iou-threshold=0.5
pre-cluster-threshold=0.4
If I set the interval of peopleNet for skipping frame, should I need to change interval of bodypose?
I set the interval = 1 of peopleNet but when I open the json output file, it still infer every frame, I still get the information for every frame. Can I know why?