Hi. I have a simple model which i trained using tensorflow. After that i converted it to ONNX and tried to make inference on my Jetson TX2 with JetPack 4.4.0 using TensorRT, but results are different. That’s how i get inference model using onnx (model has input [-1, 128, 64, 3] and output [-1, 128]…

Hi, Sorry to miss the array validation shared above. Based on your implementation: context->execute(1, buffers); output.download(result); There is no synchronized mechanism between GPU tasks and CPU tasks. So CPU may try to copy the buffer back before the inference job is done. Would you mind …

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

Robotics & Edge Computing Jetson Systems Jetson TX2

Topic		Replies	Views
Output from ONNX inference and trt inference are different Jetson TX2 tensorrt , tensorflow , nvbugs	5	1070	May 14, 2021
Nvinfer input formats issue Jetson Nano jetson-inference	23	2898	October 12, 2021
TensorRT with ONNX model and RGB opencv data TensorRT tensorrt , opencv , cuda	6	3664	April 28, 2021
TensorRT get different result in python and c++ TensorRT	21	3418	August 24, 2022
Always same output vlaues TensorRT	9	2603	July 14, 2021
Get wrong result when I using tensorRT to do inference, am I wrong to use ? Jetson TX2	17	3274	June 19, 2018
TensorRT C++ result was wired and changed everytime I do the same inference TensorRT	3	841	May 17, 2021
Kernel weights has count 2304 but 32640 was expected Jetson TX2 tensorrt , nvbugs	22	4971	May 12, 2022
YOLOv4 TensorRT inference results wayy off, but onnxruntime is not TensorRT tensorrt	6	1175	June 7, 2022
TensorRT 8 : C++ inference gives different results compared to tensorflow python inference TensorRT	7	1552	October 5, 2021

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

Related topics