[property]
gpu-id=0
net-scale-factor=0.007843
# Since the model input channel is 3, and pre-processing of UNET TAO requires BGR format, set the color format to BGR.
# 0-RGB, 1-BGR, 2-Gray
#model-color-format=1# For grayscale, this should be set to 2
offsets=127.5;127.5;127.5
labelfile-path=/opt/nvidia/deepstream/deepstream/semantic_segment/640_640/new/labels.txt
##Replace following path to your model file
# You can provide the model as etlt file or convert it to tensorrt engine offline using tao-converter and
# provide it in the config file. If you are providing the etlt model, do not forget to provide the model key.
#tlt-encoded-model=/opt/nvidia/deepstream/deepstream/semantic_segment/640_640/new/model.int8.etlt
tlt-model-key=nvidia_tlt
# Argument to be used if you are using an tensorrt engine
model-engine-file=/opt/nvidia/deepstream/deepstream/semantic_segment/640_640/new/trt_int8.engine
#model-engine-file=/opt/nvidia/deepstream/deepstream-6.0/semantic_segment/640_640/new/model.int8.etlt_b1_gpu0_fp16.engine
infer-dims=3;640;640
batch-size=1

## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=2
num-detected-classes=22
interval=0
gie-unique-id=1

## 0=Detector, 1=Classifier, 2=Semantic Segmentation (sigmoid activation), 3=Instance Segmentation, 100=skip nvinfer postprocessing
network-type=2

#output-tensor-meta=1 # Set this to 1 when network-type is 100

output-blob-names=argmax # If you had used softmax for segmentation model, it would have been replaced with argmax by TAO for optimization.
                           # Hence, you need to provide argmax_1
segmentation-threshold=0.0
##specify the output tensor order, 0(default value) for CHW and 1 for HWC
segmentation-output-order=0

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