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: https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/blob/master/yolo/data/yolov3-calibration.table
How do I use the calibration table? I found the method
tensorrt.tensorrt.IInt8Calibrator.read_calibration_cache()
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?