Yolov4 on tao gives batchedNMS error

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc)
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)

| Model | Version | Status |
±------------------±--------±----------------------------------------------------------------------------------------------------------------------+
| tao_yolo_v4_model | 1 | UNAVAILABLE: Internal: onnx runtime error 10: Load model from /models/tao_yolo_v4_model/1/model.onnx failed:This is a |
| | | n invalid model. In Node, (“BatchedNMS_N”, BatchedNMSDynamic_TRT, “”, -1) : (“box”: tensor(float),“cls”: tensor(float |
| | | ),) → (“BatchedNMS”: tensor(int32),“BatchedNMS_1”: tensor(float),“BatchedNMS_2”: tensor(float),“BatchedNMS_3”: tenso |
| | | r(float),) , Error No Op registered for BatchedNMSDynamic_TRT with domain_version of 12

2

this is while we use the custom trianed yolov4 and try to load on the triton server.

UNAVAILABLE: Internal: onnx runtime error 10: Load model from /models/tao_yolo_v4_model/1/model.onnx failed:This is a |
| | | n invalid model. In Node, (“BatchedNMS_N”, BatchedNMSDynamic_TRT, “”, -1) : (“box”: tensor(float),“cls”: tensor(float |
| | | ),) → (“BatchedNMS”: tensor(int32),“BatchedNMS_1”: tensor(float),“BatchedNMS_2”: tensor(float),“BatchedNMS_3”: tenso |
| | | r(float),) , Error No Op registered for BatchedNMSDynamic_TRT with domain_version of 15

3

Please generate to tensorrt engine(i.e., model.plan). Refer to GitHub - NVIDIA-AI-IOT/tao-toolkit-triton-apps: Sample app code for deploying TAO Toolkit trained models to Triton.

4

Just wanted to confirm if this solution works for yolov4 and on a AGX orin development kit?

5

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Yes, we can run inference while using tensorrt engine in Orin device.

6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.