# Error Using Custom ONNX TRT Model with Deepstream **URL:** \ **Category:** Deep Learning (Training & Inference)\ **Created:** [August 3, 2020, 7:17pm UTC](https://forums.developer.nvidia.com/t/error-using-custom-onnx-trt-model-with-deepstream/145227 "2020-08-03T19:17:24Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![isdavis754](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@isdavis754](https://forums.developer.nvidia.com/u/isdavis754)\ **Post date:** [August 3, 2020, 7:17pm UTC](https://forums.developer.nvidia.com/t/error-using-custom-onnx-trt-model-with-deepstream/145227/1 "2020-08-03T19:17:24Z")
I created a custom SSD-Mobilenet-v1 model as outlined in Hello AI World ([jetson-inference/pytorch-ssd.md at master · dusty-nv/jetson-inference · GitHub](https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-ssd.md)). After it successfully ran in using the script in the tutorial, I copied the model file into samples file aand attempted to run with the deepstream app. I modified the the config files to reflect the path of the TRT engine, labels, and onnx file paths. When I run the deepstream app, I get the error below. I am new at this, so any assistance is appreciated. Ian gmnano1@gmnano1:/opt/nvidia/deepstream/deepstream-5.0/samples$ deepstream-app -c /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5-source2\_1080p\_ssd-gmais16-v1\_tracker\_tiled\_display\_fp16\_nano.txt -t (deepstream-app:11900): GLib-GObject-WARNING \*\*: 14:51:10.911: g\_object\_set\_is\_valid\_property: object class ‘GstNvArgusCameraSrc’ has no property named ‘maxperf’ (deepstream-app:11900): GLib-GObject-WARNING \*\*: 14:51:10.922: g\_object\_set\_is\_valid\_property: object class ‘GstNvArgusCameraSrc’ has no property named ‘maxperf’ 0:00:04.275830319 11900 0x4715890 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/ssd-gmias16-v1/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 3000x17 2 OUTPUT kFLOAT boxes 3000x4 0:00:04.276057568 11900 0x4715890 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() \ [UID = 1]: Backend has maxBatchSize 1 whereas 2 has been requested 0:00:04.276090746 11900 0x4715890 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: deserialized backend context :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/ssd-gmias16-v1/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine failed to match config params, trying rebuild 0:00:04.282214642 11900 0x4715890 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() \ [UID = 1]: Trying to create engine from model files ERROR: failed to build network since there is no model file matched. ERROR: failed to build network. 0:00:04.282623044 11900 0x4715890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() \ [UID = 1]: build engine file failed 0:00:04.282669244 11900 0x4715890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: build backend context failed 0:00:04.282700339 11900 0x4715890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() \ [UID = 1]: generate backend failed, check config file settings 0:00:04.282765237 11900 0x4715890 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start:\ error: Failed to create NvDsInferContext instance 0:00:04.282792061 11900 0x4715890 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start:\ error: Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5\_config\_infer\_primary\_nano.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED \*\* ERROR: main:651: Failed to set pipeline to PAUSED Quitting ERROR from primary\_gie: Failed to create NvDsInferContext instance Debug info: /dvs/git/dirty/git-master\_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(781): gst\_nvinfer\_start (): /GstPipeline:pipeline/GstBin:primary\_gie\_bin/GstNvInfer:primary\_gie: Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5\_config\_infer\_primary\_nano.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED App run failed gmnano1@gmnano1:/opt/nvidia/deepstream/deepstream-5.0/samples$ deepstream-app -c /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5-source2\_1080p\_ssd-gmais16-v1\_tracker\_tiled\_display\_fp16\_nano.txt -t (deepstream-app:12186): GLib-GObject-WARNING \*\*: 15:01:57.907: g\_object\_set\_is\_valid\_property: object class ‘GstNvArgusCameraSrc’ has no property named ‘maxperf’ (deepstream-app:12186): GLib-GObject-WARNING \*\*: 15:01:57.909: g\_object\_set\_is\_valid\_property: object class ‘GstNvArgusCameraSrc’ has no property named ‘maxperf’ 0:00:03.609782770 12186 0x3c0bf890 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/ssd-gmias16-v1/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 3000x17 2 OUTPUT kFLOAT boxes 3000x4 0:00:03.610009912 12186 0x3c0bf890 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() \ [UID = 1]: Backend has maxBatchSize 1 whereas 2 has been requested 0:00:03.610041267 12186 0x3c0bf890 WARN nvinfer gstnvinfer.cpp:599:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: deserialized backend context :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/ssd-gmias16-v1/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine failed to match config params, trying rebuild 0:00:03.616261909 12186 0x3c0bf890 INFO nvinfer gstnvinfer.cpp:602:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() \ [UID = 1]: Trying to create engine from model files ERROR: failed to build network since there is no model file matched. ERROR: failed to build network. 0:00:03.616664056 12186 0x3c0bf890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() \ [UID = 1]: build engine file failed 0:00:03.616709526 12186 0x3c0bf890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: build backend context failed 0:00:03.616742079 12186 0x3c0bf890 ERROR nvinfer gstnvinfer.cpp:596:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() \ [UID = 1]: generate backend failed, check config file settings 0:00:03.616806664 12186 0x3c0bf890 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start:\ error: Failed to create NvDsInferContext instance 0:00:03.616834061 12186 0x3c0bf890 WARN nvinfer gstnvinfer.cpp:781:gst\_nvinfer\_start:\ error: Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5\_config\_infer\_primary\_nano.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED \*\* ERROR: main:651: Failed to set pipeline to PAUSED Quitting ERROR from primary\_gie: Failed to create NvDsInferContext instance Debug info: /dvs/git/dirty/git-master\_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(781): gst\_nvinfer\_start (): /GstPipeline:pipeline/GstBin:primary\_gie\_bin/GstNvInfer:primary\_gie: Config file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/MOD5\_config\_infer\_primary\_nano.txt, NvDsInfer Error: NVDSINFER\_CONFIG\_FAILED App run failed