Deepstream_pose_estimation doesn't show pose estimation skeleton

[edit_or]

I am testing deepstream_pose_estimation.
With provided onnx file, I see some detection.

But when I use the following two models, detection just show small white circles only, no green lines.

resnet18_baseline_att_224x224_A
densenet121_baseline_att_256x256_B

What should I change?
I managed to work with mp4 file. The original program uses h264 raw stream.
Can detection accuracy drop using mp4 format?

[bcao]

Hey could you share your setup with us?

[edit_or]

Which set up file? Is it config file?

[edit_or]

I sent by private message all files (cpp file that can run mp4 file, models, config file and test video).
Only pose_estimation.onnx works (still not very good). The other models don’t work.