Reading calibration table

I would like to run YOLOv3 on TensorRT on Jetson Xavier in int8 mode, using Python. The YOLOv3 TensorRT sample works perfectly for me.

I found the calibration table for yolov3 here:

How do I use the calibration table? I found the method


but I don’t know how to use it in my code.

Alternatively, how can I convert “yolo_107: 3cb957a3” directly to the (min_float, max_float) for every layer?

Hello, I have the same question.

How to read these Hex numbers to get information about the calibration?

Hello, any updates?