Running tlt_retinanet with deepstream_python_apps (deepstream_test3_app)

[_blackShark]

Hardware Platform ( GPU): GTX-1050
DeepStream Version: 5.1

I modified the own config dstest3_pgie_tlt_config.txt which was similar backbone dstest3_pgie_config.txt

The config file is changed as bellow:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-file=/opt/nvidia/deepstream/deepstream-5.1/sources/python/models/retinanet/retinanet_resnet18.etlt
#proto-file=/opt/nvidia/deepstream/deepstream-5.1/samples/models/Primary_Detector/resnet10.prototxt
#model-engine-file=/opt/nvidia/deepstream/deepstream-5.1/sources/python/models/retinanet/retinanet_resnet18.etlt_b1_gpu0_int8.engine
model-engine-file=/opt/nvidia/deepstream/deepstream-5.1/sources/python/resnet34_peoplenet_pruned.etl_b1_gp0_int8.engine
labelfile-path=/opt/nvidia/deepstream/deepstream-5.1/sources/python/configs/retinanet_tlt/retinanet_labels.txt
int8-calib-file=/opt/nvidia/deepstream/deepstream-5.1/sources/python/models/retinanet/cal.bin
force-implicit-batch-dim=1
batch-size=1
process-mode=1
model-color-format=0
network-mode=1
num-detected-classes=5
interval=0
gie-unique-id=1
output-blob-names=conv2d_bbox;conv2d_cov/Sigmoid

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

I have error compiling code as shown:

The mode-file and calib-file which I take from github:deepstream_tlt_apps.

[bcao]

Can you try fakesink instead of EGLsink

[_blackShark]

thanks for your support, but I has also met this problem.
I’d like to use tlt + custom-data for deepstream_python_apps

[bcao]

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

You mean the issue persist when you are using fakesink?