NVIDIA Developer Forums

Inference of model using tensorflow/onnxruntime and TensorRT gives different result

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2

Topic		Replies	Views	Activity
Output from ONNX inference and trt inference are different Jetson TX2 tensorrt , tensorflow , nvbugs	6	847	October 18, 2021
Nvinfer input formats issue Jetson Nano jetson-inference	23	2403	October 12, 2021
TensorRT with ONNX model and RGB opencv data TensorRT tensorrt , opencv , cuda	6	3414	April 28, 2021
TensorRT get different result in python and c++ TensorRT	21	2936	August 24, 2022
Always same output vlaues TensorRT	10	2378	October 12, 2021
Get wrong result when I using tensorRT to do inference, am I wrong to use ? Jetson TX2	18	3035	October 18, 2021
TensorRT C++ result was wired and changed everytime I do the same inference TensorRT	3	710	May 17, 2021
Kernel weights has count 2304 but 32640 was expected Jetson TX2 tensorrt , nvbugs	23	4544	May 12, 2022
YOLOv4 TensorRT inference results wayy off, but onnxruntime is not TensorRT tensorrt	7	971	June 7, 2022
TensorRT 8 : C++ inference gives different results compared to tensorflow python inference TensorRT	7	1383	October 5, 2021