TensorRT: Int8 calibration with hand-tuned scale factors

I’m looking to do int8 calibration for a particular model. The scales generated by calibration are not performing adequately. Is there a way to hand-tune the scales?

I’ve noticed that the cached calibration file contains a hex value for each layer. Can you explain what these values represent? That way it becomes possible to try to tune these values for improved model accuracy.



Here is an useful tutorial for INT8 on TensorRT:

You can also check this source for calibrator information:


Thanks for the fast response and the additional resources! I have actually already implemented a calibration with TensorRT. I am curious if you can explain what the output values mean?

The cached calibration is a set 64-bit hex values. How are these used as scales?

Hmm sorry it’s actually a 32-bit hex value. Looks like it represents a float. Is this is the scale created by calibration?


Please check this page for information:


Same question!