Hey, could you try as DeepStream SDK FAQ - #9 by mchi to make sure the input object for sgie w/o DS pipeline are the same.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Secondary model which is a mask classifier outputs first entry in label.txt file | 8 | 477 | October 12, 2021 | |
| Degradation of Face Detection Performance in Multi-Stream Inference Pipeline | 7 | 49 | May 23, 2025 | |
| Inconsistent result when secondary engine ran through DeepStream SDK | 11 | 900 | October 12, 2021 | |
| Secondary detector | 3 | 839 | October 12, 2021 | |
| How to load resnet (google facenet) model to deepstream and pass the output to the other trained model | 11 | 1662 | October 12, 2021 | |
| Preprocessing image for secondary classifier in Deepstream | 4 | 1071 | October 12, 2021 | |
| Deepstream default model for object detection | 2 | 368 | September 29, 2023 | |
| How to apply a mask to primary detections before feeding into secondary detector | 3 | 29 | December 30, 2024 | |
| Classification accuracy mismatch between running same resnet18 engine on tensorrt and deepstream | 0 | 339 | November 30, 2023 | |
| Secondary-GIE result in DeepStream messed, python tensorrt api works fine | 6 | 951 | August 26, 2021 |