I have trained TAO toolkit with custom data and i successfully generated the model after purning ,but when i put it in Deepstream testapp3 .I am getting less speed after 5th video input.(Deepstream testapp3 will detect 16 video input at a time)
Model size before puning : 43 MB after purning : 16MB
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| TAO trained custom model (DetectNetV2 + RESNET10) deployed in Deepstream is having low fps | 5 | 735 | February 14, 2023 | |
| TAO Toolkit efficientnet B4 and efficientnet B5 fps | 13 | 1155 | February 1, 2022 | |
| TAO pretrained model performance metrics changed, documentation tables need clarified | 3 | 600 | August 16, 2022 | |
| TAO toolkit: Accuracy drops classiffication tf2 when trt engine is generated | 3 | 18 | September 18, 2024 | |
| Is there any way to make deepstream_tlt_apps faster? | 9 | 307 | October 12, 2021 | |
| Why does deepstream run slower and slower | 4 | 387 | July 19, 2022 | |
| Mispredictions with Custom trained PoseClassificationNet when integrated with DeepStream Pose Classification | 4 | 291 | February 5, 2024 | |
| Tao vs engine performance | 2 | 409 | March 16, 2022 | |
| Deepstream: FPS issue while saving images in test5 app | 1 | 436 | January 8, 2020 | |
| Fps downgrade during deepstream inference | 4 | 481 | December 21, 2021 |