I have created TAO model yolov4. It is onnx format but i am not able to run it using onnxruntime-gpu so i found that it contains custome layers, i reffered following links:- BatchedNMS_TRT: could not find any supported formats consistent with input/output data types · Issue #954 · NVIDIA/TensorRT …

[image] sarvatmak: Now i need it to run with gpu onnx runtime. Similar to topic Errors while reading ONNX file produced by TAO 5 - #10 by Morganh .

Unable to create plugin for BatchedNMSDynamic_TRT for onnx tao model using graphsurgeon

Morganh July 18, 2024, 4:52pm 2

Topic		Replies	Views
My Yolov4 tf2checkpoint->save_model->onnx->trt TensorRT tensorrt , jetson-inference	3	484	November 1, 2021
Yolov4 on tao gives batchedNMS error TAO Toolkit	5	306	February 12, 2024
Tf2 checkpoint->save_model->onnx->trt (onnx->trt failed) TensorRT tensorrt , jetson	1	535	November 1, 2021
Errors while reading ONNX file produced by TAO 5 TAO Toolkit	11	1767	September 6, 2023
Do we have to use BatchedNMSDynamic_TRT in the model output by ONNX? TAO Toolkit onnx	2	517	October 26, 2023
[ERROR] Model has dynamic shape but no optimization profile specified TAO Toolkit	2	2433	September 15, 2021
Usability of the exported onnx file TAO Toolkit	3	604	October 3, 2023
Failed to convert onnx to trt build_engine.py TensorRT	5	1397	May 25, 2022
Adding BatchedNMSDynamic_TRT plugin in the ssd mobileNet onnx model TensorRT	4	1873	September 7, 2021
TAO Toolkit 4.0, Yolo v4 not working with Deepstream nvinfer - parseModel: Failed to parse ONNX model TAO Toolkit onnx , tao , deepstream61	6	964	February 20, 2023