App run failed

[1.umairjavaid]

I have downloaded the pruned resnet34-peoplenet model from ngc. After setting the tlt-encoded-model path to the downloaded etlt file, in the config_infer_primary_peoplnet.txt file, I am running the following command deepstream-app -c deepstream_app_source1_peoplenet.txt

** ERROR: <main:655>: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Configuration file parsing failed
Debug info: gstnvinfer.cpp(769): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models/config_infer_primary_peoplenet.txt
App run failed

config_infer_primary_peoplenet.txt (2.1 KB)
deepstream_app_source1_peoplenet.txt (3.3 KB)

why am I getting this error, how can I fix it?

• gtx 1660
• DeepStream 5.1

[Amycao]

@1.umairjavaid

ERROR from primary_gie: Configuration file parsing failed

Error is from here, can you remove the cache and get more log?

[1.umairjavaid]

What do you mean by remove the cache?

[Amycao]

rm ~/.cache/gstreamer-1.0/ -rf

[1.umairjavaid]

I had given incorrect path. After fixing the path to etlt file. It is running properly. Could you be kind enough to see my other question?

[1.umairjavaid]

Can you tell me why do we have to specify model-engine-file twice. First in the main config file and then in the model config file?

[Amycao]

You do not need to specify twice, it’s same.