Description i have trained a model with pytorch and export it to onnx format model, this onnx model predicts correct value. but when i convert it to tensorrt engine, it gives wrong inference. i use polygraphy to check the difference of the two. my command is : polygraphy run detector_corrector.…

Tensorrt8.5 inference different with origin onnx model

liwenjudetiankong December 5, 2022, 3:46am 9

please reference this post, Tensorrt8.5 inference different with origin onnx model
i have upload test code, onnx and trt runtime just give totally diffrent result.

Topic		Replies	Views
Onnx vs tensorrt different inference result TensorRT	3	3230	November 29, 2022
TensorRT 8 : C++ inference gives different results compared to tensorflow python inference TensorRT	7	1362	October 5, 2021
8bit quantized onnx file and its 8bit engine inference results differ TensorRT tensorrt	2	688	November 21, 2021
TensorRT python API inference is inconsistent with trtexec inference TensorRT tensorrt	1	1006	February 28, 2023
Tensorrt 8.6 GA : C++ Inference gives diffrence results compared to onnx \|\| pt model python inference TensorRT	3	637	September 20, 2023
Different engines give different inference results when using the same onnx model and giving the same input TensorRT	4	966	December 31, 2023
Two machines with very similar SW stack but different GPUs generate different folded model using the Polygraphy tool on the same model onnx input TensorRT	7	816	June 22, 2022
Incorrect inference results after converting from ONNX to TRT with trtexec TensorRT tensorrt , python , onnx	4	1593	December 9, 2022
Differences between tensorflow model inference and tensorRT model inference TensorRT tensorrt , tensorflow	6	1774	September 14, 2022
TensorRT gives diffent results than ONNX and Pytorch TensorRT	8	1593	September 28, 2023