You can refer DeepStream SDK FAQ - #9 by mchi to dump the inference input and see if there are any differences?
bcao
7
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Deepstream secondary gie classification results are incorrect | 1 | 184 | July 5, 2024 | |
| Inaccurate GIE classification after converting to TensorRT | 17 | 845 | July 8, 2024 | |
| Implement SecondaryGIE with custom classification model causing Perf to decrease to 0fps | 1 | 453 | July 22, 2020 | |
| Custom Secondary Network | 15 | 1455 | August 23, 2022 | |
| Inconsistent result when secondary engine ran through DeepStream SDK | 10 | 1177 | March 9, 2020 | |
| Deepstream secondary gie trouble running | 18 | 736 | May 21, 2024 | |
| Deepstream secondary gie use googlenet trained by nvidia/digits | 4 | 483 | June 1, 2022 | |
| Deepstream 6.3 Secondary Gie | 4 | 378 | May 9, 2024 | |
| Difference between predictions of exported TensorRT engine and PyTorch pth models | 22 | 2821 | March 14, 2023 | |
| Classification accuracy mismatch between running same resnet18 engine on tensorrt and deepstream | 0 | 383 | November 30, 2023 |