How to run ped-100 in Deepstream

hi,

I am having trouble using a pretrained network in deepstream. I took the pednet downloaded from the hello ai world tool and I tried to integrate it in the first sample app of deepstream changing the original dstest1pgie_config

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-file=…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel
proto-file=…/…/…/…/samples/models/Primary_Detector/resnet10.prototxt
model-engine-file=…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
labelfile-path=…/…/…/…/samples/models/Primary_Detector/labels.txt
int8-calib-file=…/…/…/…/samples/models/Primary_Detector/cal_trt.bin
force-implicit-batch-dim=1
batch-size=1
network-mode=1
num-detected-classes=4
interval=0
gie-unique-id=1
output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid
#scaling-filter=0
#scaling-compute-hw=0

[class-attrs-all]
pre-cluster-threshold=0.2
eps=0.2
group-threshold=1

In:

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-file=…/…/…/…/samples/models/Prove_Personali/ped-100/snapshot_iter_70800.caffemodel
proto-file=…/…/…/…/samples/models/Prove_Personali/ped-100/original.prototxt
model-engine-file=…/…/…/…/samples/models/Prove_Personali/ped-100/snapshot_iter_70800.caffemodel.1.1.7103.GPU.FP16.engine
labelfile-path=…/…/…/…/samples/models/Prove_Personali/ped-100/class_labels.txt
int8-calib-file=…/…/…/…/samples/models/Primary_Detector/cal_trt.bin
force-implicit-batch-dim=1
batch-size=1
network-mode=1
num-detected-classes=1
interval=0
gie-unique-id=1
output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid
#scaling-filter=0
#scaling-compute-hw=0

[class-attrs-all]
pre-cluster-threshold=0.2
eps=0.2
group-threshold=1

I didnt modified the path of cal_trt.bin cause this file don’t exist in the ped-100 network folder downloaded by hello ai world.
could this be the problem?

when i run the application with an example video, the preview starts but the fps are very low (0.5 / sec) and nothing is recognized.

thanks in advance for the help

Please check http://sw-mobile-docs/DRAFT/DeepStream_32_2019/#page/DeepStream_Development_Guide/deepstream_custom_model.html#