To use pre-trained models it is a preferred practice to normalize the input images with imagenet standards.

mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

How are these parameters derived?


These are calculated based on millions of images of ImageNet.

Ref - SO
Ref - MachinelearningMastery


According to the Pytorch's docs, you can calculate mean and std using this:

import torch
from torchvision import datasets, transforms as T

transform = T.Compose([T.Resize(256), T.CenterCrop(224), T.ToTensor()])
dataset = datasets.ImageNet(".", split="train", transform=transform)

means = []
stds = []
for img in subset(dataset):

mean = torch.mean(torch.tensor(means))
std = torch.mean(torch.tensor(stds))


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.