Unable to get any object detected

[initmahesh]

I am standing in front of camera and expecting 1 object to be detected, but getting no object detected

Here are some fundamental design suggestion to make this sample better

• Please add display support as without that its hard or impossible to debug issues like above
• Stop sending message to Iot Hub when no object is detected
• Send a Json object as results to implement easy checks rather string

Logs from inference module ::

PROCESSED 1 IN 0.18634247779846191 s
cam1 Results @05:45:02
172.18.0.4 - - [11/Sep/2019 12:45:02] "POST / HTTP/1.1" 200 -
Confirmation[0] received for message with result = OK
INFERENCE TIME (PURE ONNXRUNTIME) 47.68824577331543 ms
POST PROCESSING TIME 116.80459976196289 ms
TOTAL INFERENCE TIME 164.92486000061035 ms
NUMBER OBJECTS DETECTED: 0
PROCESSED 1 IN 0.18532228469848633 s
cam1 Results @05:45:02
172.18.0.4 - - [11/Sep/2019 12:45:02] "POST / HTTP/1.1" 200 -
Confirmation[0] received for message with result = OK
INFERENCE TIME (PURE ONNXRUNTIME) 46.94080352783203 ms
POST PROCESSING TIME 118.45207214355469 ms
TOTAL INFERENCE TIME 165.87448120117188 ms

Message send to cloud per sec even if no object is detected ::

[IoTHubMonitor] [5:45:58 AM] Message received from [a_jetson_Nano/PostProcessingModule]:
"cam1 Results @05:45:58 "
[IoTHubMonitor] [5:45:58 AM] Message received from [a_jetson_Nano/PostProcessingModule]:
"cam1 Results @05:45:58 "

[manashgoswami]

Hi Mahesh. Thanks for the suggestion. If you want to submit a PR with the updates from your clone/demo I could be happy to merge them to master. This will give our users the option to use a display if it suites their demo needs.

[xlegend1024]

Hi, I'm also no inference result from the logs either. Sometime I see a Cat or Cow as inference result which is not there in front of a camera. I dumped images that capture by the CameraCaptureModule, but it was clean images that have no Cat nor Cow.

[IoTHubMonitor] [12:06:31 PM] Message received from [nvidia-ai-dk-01/PostProcessingModule]:
"MTCSeattle Results @12:06:30 "
[IoTHubMonitor] [12:06:33 PM] Message received from [nvidia-ai-dk-01/PostProcessingModule]:
"MTCSeattle Results @12:06:32 cat confidence 0.513495716317663"
[IoTHubMonitor] [12:06:35 PM] Message received from [nvidia-ai-dk-01/PostProcessingModule]:
"MTCSeattle Results @12:06:34 "
[IoTHubMonitor] [12:06:37 PM] Message received from [nvidia-ai-dk-01/PostProcessingModule]:
"MTCSeattle Results @12:06:36 "

Is there a way to fix this? Don't know where to start.

[srinivasbakki]

Could anybody get this working ? Unable to detect any objects. Additionally i tried separate build with onnx v1.20 - opset8, tensorrt 7, cuda 10.0 , i.e jetpack 4.3 No success with inference.

172.18.0.4 - - [03/Aug/2020 19:05:53] "POST / HTTP/1.1" 200 -
INFERENCE TIME (PURE ONNXRUNTIME) 81.08639717102051 ms
POST PROCESSING TIME 89.10250663757324 ms
TOTAL INFERENCE TIME 170.54319381713867 ms
NUMBER OBJECTS DETECTED: 0
PROCESSED 1 IN 0.6483609676361084 s
Sent message to client
SUCCESSFULLY STORED
cam1 Results @06:35:53

And yes, i did test this with tinyyolo v2.