[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
custom-network-config=yolov5_vehicle.cfg
model-file=yolov5_vehicle.wts
model-engine-file=model_b1_gpu0_fp32.engine
labelfile-path=labels_vehicle.txt
batch-size=1
# Data format to be used by inference; Integer 0: FP32 1: INT8 2: FP16
network-mode=0
num-detected-classes=63
# Number of consecutive batches to be skipped for inference
interval=0
# Unique ID to be assigned to the GIE to enable the application and other elements to identify detected bounding boxes and labels
gie-unique-id=1
# Mode (primary or secondary) in which the element is to operate on (ignored if input-tensor-meta enabled); Integer 1=Primary 2=Secondary
process-mode=1
# Type of network | 0: Detector | 1: Classifier | 2: Segmentation | 3: Instance Segmentation
network-type=0
# cluster-mode = 2 | NMS
cluster-mode=2
maintain-aspect-ratio=1
# Name of the custom bounding box parsing function. If not specified, Gst-nvinfer uses the internal function for the resnet model provided by the SDK
parse-bbox-func-name=NvDsInferParseYolo
# Absolute pathname of a library containing custom method implementations for custom models
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet

# For detector: output-blob-names=coverage;bbox . For multi-label classifiers: output-blob-names =coverage_attrib1;coverage_attrib2
output-blob-names=coverage;bbox

[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
# Keep only top K objects with highest detection scores.
topk=300