# Deepstream app with triton server **URL:** \ **Category:** DeepStream SDK\ **Created:** [May 2, 2022, 2:22am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149 "2022-05-02T02:22:33Z")\ **Posts on this page:** 13\ **Page:** 1
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 2, 2022, 2:22am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/1 "2022-05-02T02:22:33Z")
Please provide complete information as applicable to your setup. **• Hardware Platform (Jetson / GPU)** Tesla T4 **• DeepStream Version** 6.1 **• JetPack Version (valid for Jetson only)** **• TensorRT Version** 7.1 **• NVIDIA GPU Driver Version (valid for GPU only)** cuda 11.4 **• Issue Type( questions, new requirements, bugs)** **• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)** **• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)** i am not able to get metadata while inferencing from the custom deepstream app , could you provide an example for it . ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [May 3, 2022, 2:07pm UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/3 "2022-05-03T14:07:14Z")
Hi, I think you can refer to DeepStream sample - apps/sample\_apps/deepstream-user-metadata-test It demonstrates how to add custom or user-specific metadata to any component of DeepStream. The test code attaches a 16-byte array filled with user data to the chosen component. The data is retrieved in another component. This app uses resnet10.caffemodel for detection. ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 4, 2022, 2:34am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/4 "2022-05-04T02:34:46Z")
is there a relavent python app , deepstream-user-metadata-test is in C ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [May 5, 2022, 7:16am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/5 "2022-05-05T07:16:53Z")
yes, you can refer to the DS python samples under [deepstream\_python\_apps/apps at master · NVIDIA-AI-IOT/deepstream\_python\_apps · GitHub](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps) , e.g. [deepstream-imagedata-multistream](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps/deepstream-imagedata-multistream) ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 6, 2022, 7:12am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/6 "2022-05-06T07:12:12Z")
im doing Image inferencing , If i use **nvinfer** , i get the metadata , But if i use **nvinferserver** , i dont get the metadata . im able to use “Primary\_Detector” model through nvinferserver .where i get the metadata. Custom use -cases im not able to get it. ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [May 9, 2022, 12:41am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/7 "2022-05-09T00:41:53Z")
> [@h9945394143](#): > > But if i use **nvinferserver** , i dont get the metadata . [https://github.com/NVIDIA-AI-IOT/deepstream\_python\_apps/tree/master/apps/deepstream-ssd-parser](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps/deepstream-ssd-parser) [https://github.com/NVIDIA-AI-IOT/deepstream\_python\_apps/blob/master/apps/deepstream-ssd-parser/dstest\_ssd\_nopostprocess.txt#L63](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/blob/master/apps/deepstream-ssd-parser/dstest_ssd_nopostprocess.txt#L63) ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 12, 2022, 3:59pm UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/9 "2022-05-12T15:59:51Z")
can we customize this above example parser for all kinds of models ? such as onnx , TernsorRT engine files ? ---
**Author:** ![mchi](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/mchi/32/14043_2.png) [@mchi](https://forums.developer.nvidia.com/u/mchi)\ **Post date:** [May 13, 2022, 2:48am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/10 "2022-05-13T02:48:05Z")
yes! ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 13, 2022, 4:35am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/11 "2022-05-13T04:35:06Z")
my 4 output layers of my ONNX model are **[“output”, “573”, “625”,“677”]** how should i fill **num\_detection\_layer , score\_layer , class\_layer , box\_layer** parameters in ssd\_parser.py ? ```auto def nvds_infer_parse_custom_tf_ssd(output_layer_info, detection_param, box_size_param, nms_param=NmsParam()): """ Get data from output_layer_info and fill object_list with several NvDsInferObjectDetectionInfo. Keyword arguments: - output_layer_info : represents the neural network's output. (NvDsInferLayerInfo list) - detection_param : contains per class threshold. (DetectionParam) - box_size_param : element containing information to discard boxes that are too small. (BoxSizeParam) - nms_param : contains information for performing non maximal suppression. (NmsParam) Return: - Bounding boxes. (NvDsInferObjectDetectionInfo list) """ **num_detection_layer = layer_finder(output_layer_info, "num_detections")** **score_layer = layer_finder(output_layer_info, "detection_scores")** **class_layer = layer_finder(output_layer_info, "detection_classes")** **box_layer = layer_finder(output_layer_info, "detection_boxes")** ``` ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [May 18, 2022, 11:14am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/12 "2022-05-18T11:14:33Z")
im able to get the metadata . But the bounding box is not visible … How to use bounding box in **deepstream-ssd-parser** example ---
**Author:** ![yingliu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yingliu/32/136703_2.png) [@yingliu](https://forums.developer.nvidia.com/u/yingliu)\ **Post date:** [June 15, 2022, 7:33am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/13 "2022-06-15T07:33:05Z")
@h9945394143 Please allow me to close this topic as the initial question is solved, feel free to submit a new topic to discuss other topics, thanks. ---
**Author:** ![h9945394143](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@h9945394143](https://forums.developer.nvidia.com/u/h9945394143)\ **Post date:** [June 22, 2022, 3:28am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/15 "2022-06-22T03:28:09Z")
its fixed , kindly close it ---
**Author:** ![yingliu](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yingliu/32/136703_2.png) [@yingliu](https://forums.developer.nvidia.com/u/yingliu)\ **Post date:** [June 22, 2022, 3:42am UTC](https://forums.developer.nvidia.com/t/deepstream-app-with-triton-server/213149/16 "2022-06-22T03:42:34Z")
Closed on June 22, 2022, 3:42am UTC