I managed to run the back to back detectors with both models running on full frame. i.e. the secondary gie runs on full frame instead of bounding boxes from primary gie. But the output is slow. So I was thinking if we can select an ROI for the secondary to detect on. My primary is a hand detector and my secondary is a face detector. In this project, the face will not go below a certain point so there is no reason to detect it below that point. It might significantly improve performance. Any help in this regard is appreciated. Thank you.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Secondray gie for full frame | 9 | 1348 | October 12, 2021 | |
Deepstream running multiple model engines at the same time problem | 2 | 271 | December 15, 2023 | |
Question about Secondary GIE | 2 | 370 | October 12, 2021 | |
Clarification on Model Configuration and Input Handling | 6 | 24 | April 23, 2025 | |
Pipeline has a detector as primary gie and another detector as secondary gie | 2 | 647 | October 12, 2021 | |
In deepstream, how to create a multi-batch secondary model when the number of primary instances is unknown? | 4 | 483 | February 22, 2022 | |
Run classification on entire frame | 4 | 357 | May 23, 2022 | |
Secondary detector operates only on detected frames. | 5 | 802 | October 12, 2021 | |
Running a custom SSD model as secondary gie in back to back detectors | 3 | 447 | October 12, 2021 | |
May DeepStarem load multiple primary-gie or use secondary-gie0 for origin source? | 15 | 2712 | October 12, 2021 |