in deepstream-test3 use yolov7, only one source can run, >= 2 sources is error. the tip show can build engine file failed, why？please
**• Hardware Platform :Jetson
**• DeepStream Version:6.1
**• JetPack Version ：5.1
the config.txt is :
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
model-engine-file=yolov7-tiny.onnx_b1_gpu0_fp16.engine
labelfile-path=labels.txt
force-implicit-batch-dim=1
batch-size=1
process-mode=1
model-color-format=0
network-mode=2
num-detected-classes=80
interval=0
gie-unique-id=1
parse-bbox-func-name=NvDsInferParseCustomEfficientNMS
custom-lib-path=libnvds_infercustomparser.so
[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=300
as the first log shown, batch-size will become 2 if using two sources, then the application will create a new engine with batch-size 2 because the default engine is batch-size 1. there is an error “failed to build network since there is no model file matched.”, you need to set model configuration before creating a new engine.
duplicate with Deepstream-test3-app use other model run multi source(ERROR)
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.