amiroor / intraorderpreservingcalibration Goto Github PK

Hi,

Thanks for your brilliant work!

We are trying to reproduce your work. However, we run into some troubles. Specifically, we wonder how the calibration set samples are selected (e.g. random with fixed seed, etc.), which could be very important for a fair comparison with other methods. It would be very kind if you could provide some further information about the calibration set split.

Moreover, we're trying to make use of the training set logits but struggle to proceed without pretrained weights of the backbones. We notice that the training scripts are available here for experiments on CIFAR and SVHN yet others are not provided. It would help us a lot if you could share the weights of the pretrained backbones.

Thanks in advance!

Here, "model" is evaluated instead of "models", the list of k-models.
This results in evaluating the k-th model instead of an ensemble model.

Can you explain what the data format under data looks like?