Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
This project is for the paper "Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples". Some codes are from odin-pytorch.
It is tested under Ubuntu Linux 16.04.1 and Python 2.7 environment, and requries Pytorch package to be installed:
We use download links of two out-of-distributin datasets from odin-pytorch:
run_cross_entropy.sh: train the models using standard cross entropy loss.
run_joint_confidence.sh: train the models using joint confidence loss.
test.sh--dataset --outdataset --pretrainednet \ --dataset = name of in-distribution (svhn or cifar10) \ --outdataset = name of out-of-distribution (svhn, cifar10, lsun or imagenet) \ --pretrainednet = path to pretrainednet