Some problems about primary inference and secondary inference

Hello,I have four problems:

1.Can I set multi-primary inference?
2.Can I set a secondary inference after secondary inference?
3.Can secondary inference be as a detection instead of classification?
4.When I even set the config file of secondary inference ‘classifier-threshold=0’,‘input-object-min-width=1’ and ‘input-object-min-height=1’,some results of primary inference can not be classified.

the config file is:

[property]
gpu-id=0
net-scale-factor=1
model-file=/opt/nvidia/deepstream/deepstream-4.0/samples/models/Secondary_CarColor/resnet18.caffemodel
proto-file=/opt/nvidia/deepstream/deepstream-4.0/samples/models/Secondary_CarColor/resnet18.prototxt
mean-file=/opt/nvidia/deepstream/deepstream-4.0/samples/models/Secondary_CarColor/mean.ppm
labelfile-path=/opt/nvidia/deepstream/deepstream-4.0/samples/models/Secondary_CarColor/labels.txt
batch-size=16
model-color-format=1
process-mode=2
network-mode=0
is-classifier=1
output-blob-names=predictions/Softmax
classifier-async-mode=0
classifier-threshold=0
input-object-min-width=1
input-object-min-height=1
#operate-on-gie-id=1
#operate-on-class-ids=0