Hi,
It looks like you are facing a similar issue with the following comment:
The above issue can be fixed by updating the input layer name from 000_net into data.
Could you check if the same solution also works for you?
Thanks.
AastaLLL
6
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| I would like to ask how to get a int8 model? | 9 | 707 | September 27, 2021 | |
| Using a onnx model in INT8 mode for jetson Orin AGX | 15 | 840 | May 21, 2024 | |
| Int8 yolov8n on Jetson agx orin issue with deepstream | 14 | 1170 | July 5, 2023 | |
| Generate calibration file | 8 | 885 | September 27, 2021 | |
| Unable to create tensorRT engine file for yolov8s-seg model in ds7.1 | 5 | 37 | December 17, 2024 | |
| How to correctly calibrate a YOLO model in deepstream | 15 | 2552 | October 12, 2021 | |
| INT8 Yolo model conversion led to accuracy drop in deepstream | 22 | 3483 | October 2, 2021 | |
| Using trtexec to convert yolov3.onnx to int8, fp16, engine in deepstream has the same effect, and the accuracy of detection is completely wrong | 3 | 549 | October 12, 2021 | |
| Engine file and calib.table not saved in DeepStream | 6 | 878 | December 25, 2022 | |
| How to verify if QAT TRT engine is indeed INT8 on Xavier | 16 | 585 | October 5, 2022 |