The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.
Hi @Niko-k98 , once you have trained a calibration method, you can use its "transform(...)" method to convert the uncalibrated confidence estimates to calibrated ones.
Hope this helps.
Once i have calibrated my model, how can i use the calibrated model to run inference on an image