0

• Hardware Platform (Jetson / GPU) Jetson Nano 4GB, Ubuntu 18.4

• DeepStream Version marketplace.azurecr.io/nvidia/deepstream-iot2-l4t:latest

• JetPack Version 4.3

• Issue Type Output inference class is different from Model class

• How to reproduce the issue ? On DeepStream, deploy a object detection ONNX model. My model is ONNX model exported from Azure Custom Vision. My label file has 2 classes - 'Mask', 'No_Mask'. Deployment works fine and I am able to execute my model using DeepStream. However, output inference class I am getting as 'Vehicle' and 'No_Mask'. Can you please help me understand why I am getting output inference label as "Vehicle" when it is not there in my Model.

Sample output inference log {"log":" "1|324|23|380|61|Vehicle|#|||||||0"\n","stream":"stdout","time":"2021-01-05T16:15:15.614591738Z"}

{"log":" "1|324|23|380|61|Vehicle|#|||||||0"\n","stream":"stdout","time":"2021-01-05T16:15:15.614790179Z"}

{"log":" "2|141|15|365|161|No Mask"\n","stream":"stdout","time":"2021-01-05T16:15:15.614221209Z"}

Amit
  • 21
  • 3
  • Sample output inference log : {"log":" \"1|324|23|380|61|Vehicle|#|||||||0\"\n","stream":"stdout","time":"2021-01-05T16:15:15.614591738Z"} – Amit Mar 03 '21 at 05:13
  • property] gpu-id=0 net-scale-factor=1 #0=RGB, 1=BGR model-color-format=1 onnx-file=../custom_models/cans-model.onnx labelfile-path=../custom_models/cans-labels.txt ## 0=FP32, 1=INT8, 2=FP16 mode network-mode=0 num-detected-classes=2 gie-unique-id=1 is-classifier=0 maintain-aspect-ratio=1 #output-blob-names=output-blob-names=coverage;bbox parse-bbox-func-name=NvDsInferParseCustomYoloV2Tiny custom-lib-path=../custom_models/libnvdsinfer_custom_impl_Yolo_Custom_Vision.so – Amit Mar 17 '21 at 03:53
  • [sensor0] enable=1 type=Camera id=in00 location=45.293701447;-75.8303914499;48.1557479338 description=Camera Sensor coordinate=5.2;10.;11.2 – Amit Mar 17 '21 at 03:53

1 Answers1

0

You've most probably specified wrong labels file or the classes in it are wrong. It's provided in labelfile-path as

labelfile-path=labels.txt
kHarshit
  • 11,362
  • 10
  • 52
  • 71
  • I checked label path seems to be correct. Actually the device is picking 1 label from my File and second one it does not pick from my label file. Instead it shows 'Vehicle'. This confuses me as to why it is picking selectively. – Amit Mar 10 '21 at 04:24
  • Hello, I am using proper config files and text files. I am attaching config files. There are 3 files zipped. I am using only 1 primary GIE. I have 2 class in my ML Model and only the first class gets replaced with "Vehicle" text. Other class shows fine. One more fact I would like to highlight. For testing purpose, I even used a model which has 3-4 classes. And what I can see is that only first class gets replaced with text "Vehicle". Other class sees t show up fine. Please help. Amit – Amit Mar 17 '21 at 03:52
  • Can you confirm you've not declared any classes in your src files? Also, are you using deepstream-app or any other test app? – kHarshit Mar 18 '21 at 05:01