DeepStream--测试lpdnet车牌检测模型

 模型地址：https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/lpdnet/version

模型格式已经从加密的etlt格式变为onnx格式。这个模型用于从汽车图片上检测出车牌位置，模型有两个，一个用于美国车，一个用于中国车。

Nvinfer

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
labelfile-path=LPD/usa_lpd_label.txt
model-engine-file=LPD/LPDNet_usa_pruned_tao5.onnx_b16_gpu0_int8.engine
int8-calib-file=LPD/usa_cal_8.6.1.bin
onnx-file=LPD/LPDNet_usa_pruned_tao5.onnx
uff-input-dims=3;480;640;0
uff-input-blob-name=input_1
batch-size=16
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=1
##1 Primary 2 Secondary
process-mode=1
interval=0
gie-unique-id=2
#0 detector 1 classifier 2 segmentatio 3 instance segmentation
network-type=0
operate-on-gie-id=1
operate-on-class-ids=0
#no cluster
cluster-mode=3
output-blob-names=output_cov/Sigmoid:0;output_bbox/BiasAdd:0
input-object-min-height=30
input-object-min-width=40
#GPU:1  VIC:2(Jetson only)
#scaling-compute-hw=2
#enable-dla=1

[class-attrs-all]
pre-cluster-threshold=0.3
roi-top-offset=0
roi-bottom-offset=0
detected-min-w=0
detected-min-h=0
detected-max-w=0
detected-max-h=0

测试图片来自网络：

测试命令：

 gst-launch-1.0 filesrc location=Capture.JPG ! jpegdec ! videoconvert ! video/x-raw,format=I420 ! nvvideoconvert ! video/x-rawmemory:NVMM" role="presentation" style="position: relative;">memory:NVMM$memory:NVMM$,format=NV12 ! mux.sink_0 nvstreammux name=mux batch-size=1 width=1280 height=720 ! nvinfer config-file-path=./lpd_DetectNet2_us.txt ! nvvideoconvert ! video/x-rawmemory:NVMM" role="presentation" style="position: relative;">memory:NVMM$memory:NVMM$,format=RGBA ! nvdsosd ! nvvideoconvert ! video/x-raw,format=I420 ! jpegenc ! filesink location=out.jpg

测试结果：