HarrySm

Hello @TonyMou , I am not a professional, I am still a student. Please have a look [here ](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#trtexec-flags) ;) it is a flag in trtexec. Harry

Thank you very much @zerollzeng for your reply. I will try the data_loader.py and see how it works to get the correct pre-processing, I will let you know about the...

Hello @zerollzeng , I tried to run the object detection samples which does not need an images pre-processing. It works fine with EfficientDet-D0 and here is the final output below....

> Maybe you just can't apply efficientdet's eval scripts to yolov5 directly. Please solve it on your own because it's out of TensorRT's scope :-) Hello @zerollzeng , I see...

Hello @zerollzeng , I have an other question about your suggestion [here ](https://github.com/NVIDIA/TensorRT/issues/2322#issuecomment-1245240044) i am not sure but it seems to me that this scripts will generate me a fake...

Thank you very much @zerollzeng for the explanations. the EfficientDet script seems to me good for yolov5 calibration it uses COCO as input and the ONNX model then it generates...