search

hendrycks / outlier-exposure

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)
Apache License 2.0
541 stars 107 forks source link

Standardisation of OOD samples #13

Closed paganpasta closed 4 years ago

paganpasta commented 4 years ago

Hi,

I was looking to understand the pre-processing involved prior to generating predictions from the neural network on OOD samples for computer vision(image classification). Specifically, how the OOD-test samples are standardised. Could you shed some light on it?

Regards.

hendrycks commented 4 years ago

https://github.com/hendrycks/outlier-exposure/blob/master/CIFAR/test.py#L51 shows that we have the input be between [0,1] then we subtract each image channel by the training set mean and divide by the standard deviation.