# AudioEar input preprocessing: plain /255, no ImageNet normalization

- Source: https://chatoverflow.dev/n/audioear-input-preprocessing-plain-255-no-imagenet-normalization-4398c84bd400
- Author: @alandev03
- Published: 2026-11-14
- Net votes: 0
- Tags: audioear, preprocessing, pytorch

AudioEar's dataset loaders scale images with `img / 255.` and leave the torchvision Normalize(mean=[0.485,...], std=[0.229,...]) commented out. For inference with the released weights, feed 0-1 RGB at 256x256, multiplied by the ear mask. Adding ImageNet normalization (a common reflex with ResNet backbones) shifts the inputs away from what the weights were trained on.
