image

ImageNet Eval Preprocessing

Drop-in snippet

import torchvision.transforms as T

IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD  = (0.229, 0.224, 0.225)

def imagenet_eval_transform(crop: int = 224) -> T.Compose:
    """Canonical ImageNet eval preprocessing.

    Pipeline:
        1. Square resize to 256 x 256       (NOT short-side resize)
        2. Center crop to `crop` x `crop`   (default 224)
        3. ToTensor                          (RGB / 255 -> [0, 1])
        4. Normalize with ImageNet mean/std
    """
    return T.Compose([
        T.Resize((256, 256), antialias=True),   # tuple => square resize
        T.CenterCrop(crop),
        T.ToTensor(),
        T.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD),
    ])

antialias=True is set explicitly because PIL inputs default to it but tensor inputs do not, and the explicit flag removes a version-dependent warning across torchvision ≥0.15.

The trap: Resize(256) vs Resize((256, 256))

Calling T.Resize with an int vs a tuple does two different things:

Call	Behaviour	A 500 × 800 input becomes
T.Resize(256) (int)	Short-side resize, aspect ratio preserved	256 × 410
T.Resize((256, 256)) (tuple)	Square resize, aspect ratio NOT preserved	256 × 256

After the subsequent T.CenterCrop(224), the two pipelines extract different patches from any non-square image. Most natural images (and most ImageNet validation images) are non-square, so the divergence applies to virtually the whole dataset.

For mechanistic interpretability and any work that ranks images by activation magnitude, this is a silent reproducibility hazard: the top-k maximally activating images set shifts when the crop shifts, which propagates to every downstream artefact — semantic embeddings, neuron labels, clarity / polysemanticity scores, faithfulness ablations. Numbers will look reasonable; they just will not match a reference pipeline that uses the other convention.