Confident_classifier icon indicating copy to clipboard operation
Confident_classifier copied to clipboard

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Results 6 Confident_classifier issues
Sort by recently updated
recently updated
newest added

This should fix #3. Please check if the formulation is to your liking.

https://github.com/alinlab/Confident_classifier/blob/462db01967f8a96374f2ab6a534b7c81fd872d2f/src/run_joint_confidence.py#L156 I'm bit confused about why you needa multiply the KL divergence loss by the **number of classes**. I can't find it from the definition of your paper, could you...

I tried to use the source code from this repository and variations, but could not reproduce the figures seen in the paper. Could you please help me with directions to...

It seems this project is based on Python 3.x It's misleading on README -- “It is tested under Ubuntu Linux 16.04.1 and Python 2.7 environment”