Hi @AastaLLL thanks for the reply. The network i had, has outputs as scores and boxes. So i modified the NMS and NMS1 into scores and boxes and rebuilt the custom parser. Now im not getting any error. But the scripts stops saying
Segmentation fault (core dumped)
Parsed successfully as got below. But could’nt find where the error is
0:00:12.321735558 25973 0x3d53a000 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1701> [UID = 1]: deserialized trt engine from :/home/jetson/videostreams/samples/models/onx/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_0 3x300x300
1 OUTPUT kFLOAT scores 3000x3
2 OUTPUT kFLOAT boxes 3000x4
0:00:12.326119852 25973 0x3d53a000 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1805> [UID = 1]: Use deserialized engine model: /home/jetson/videostreams/samples/models/onx/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine
0:00:12.396903621 25973 0x3d53a000 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config_onx.txt sucessfully
Warning: gst-library-error-quark: Rounding muxer output width to the next multiple of 8: 304 (5): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvmultistream/gstnvstreammux.c(2299): gst_nvstreammux_change_state (): /GstPipeline:pipeline0/GstNvStreamMux:Stream-muxer
Segmentation fault (core dumped)