How to use bpnet on Jetson?

[AK51]

Hi,

I have created this question in the Nvidia forum, https://forums.developer.nvidia.com/t/how-to-run-bpnet-in-tao-toolkit/222628/6
And then, I was led to this github.
When I try to install it to my Jetson Orin, I need to change some code in order to do the MAKE

nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     export CUDA_VER=11.4
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others$     make

And when I try to run an example to verify the installation, there is error.
Sorry I am new to tao toolkit, did I miss any installtion or setup?
Note: My AGX Orin 64Gb is new and flashed with deepstream 6.1 using SDK manager.
Thx

nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app$ ./deepstream-bodypose2d-app 1 ../../../configs/bodypose2d_tao/sample_bodypose2d_model_config.txt 0 0 file:///usr/data/bodypose2d_test.png ./body2dout
(gst-plugin-scanner:15202): GStreamer-WARNING **: 16:29:49.954: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_inferserver.so': libtritonserver.so: cannot open shared object file: No such file or directory

(gst-plugin-scanner:15202): GStreamer-WARNING **: 16:29:49.969: Failed to load plugin '/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so': librivermax.so.0: cannot open shared object file: No such file or directory
Request sink_0 pad from streammux
joint Edges 1 , 8
joint Edges 8 , 9
joint Edges 9 , 10
joint Edges 1 , 11
joint Edges 11 , 12
joint Edges 12 , 13
joint Edges 1 , 2
joint Edges 2 , 3
joint Edges 3 , 4
joint Edges 2 , 16
joint Edges 1 , 5
joint Edges 5 , 6
joint Edges 6 , 7
joint Edges 5 , 17
joint Edges 1 , 0
joint Edges 0 , 14
joint Edges 0 , 15
joint Edges 14 , 16
joint Edges 15 , 17
connections 0 , 1
connections 1 , 2
connections 1 , 5
connections 2 , 3
connections 3 , 4
connections 5 , 6
connections 6 , 7
connections 2 , 8
connections 8 , 9
connections 9 , 10
connections 5 , 11
connections 11 , 12
connections 12 , 13
connections 0 , 14
connections 14 , 16
connections 8 , 11
connections 15 , 17
connections 0 , 15
Now playing: file:///usr/data/bodypose2d_test.png
WARNING: Deserialize engine failed because file path: /home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine open error
0:00:05.148199758 15201 0xaaaae3449e00 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine failed
0:00:05.304385506 15201 0xaaaae3449e00 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file :/home/nvidia/deepstream_tao_apps/configs/bodypose2d_tao/../../models/bodypose2d/model.etlt_b32_gpu0_fp16.engine failed, try rebuild
0:00:05.304678340 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: onnx2trt_utils.cpp:363: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
WARNING: [TRT]: DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU

0:11:05.334551750 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-infer-engine1> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1946> [UID = 1]: serialize cuda engine to file: /home/nvidia/deepstream_tao_apps/models/bodypose2d/model.etlt_b32_gpu0_fp16.engine successfully
INFO: [FullDims Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1:0       288x384x3       min: 1x288x384x3     opt: 32x288x384x3    Max: 32x288x384x3    
1   OUTPUT kFLOAT heatmap_out/BiasAdd:0 36x48x19        min: 0               opt: 0               Max: 0               
2   OUTPUT kFLOAT conv2d_transpose_1/BiasAdd:0 144x192x38      min: 0               opt: 0               Max: 0               

0:11:06.277470953 15201 0xaaaae3449e00 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-infer-engine1> [UID 1]: Load new model:../../../configs/bodypose2d_tao/bodypose2d_pgie_config.txt sucessfully
Decodebin child added: source
Decodebin child added: decodebin0
Running...
ERROR from element source: Resource not found.
Error details: gstfilesrc.c(532): gst_file_src_start (): /GstPipeline:pipeline/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstFileSrc:source:
No such file "/usr/data/bodypose2d_test.png"
Returned, stopping playback
Average fps 0.000233
Totally 0 persons are inferred
Deleting pipeline
nvidia@ubuntu:~/deepstream_tao_apps/apps/tao_others/deepstream-bodypose2d-app$ 

[PaRowsome]

I saw a similar issue. When I removed the file:// from the file path it worked., i.e.:
file:///usr/data/bodypose2d_test.png change it to /usr/data/bodypose2d_test.png