Models / timm / ViT-Small (Patch16, 224px, AugReg, IN21k → IN1k)

ViT-Small (Patch16, 224px, AugReg, IN21k → IN1k)

vision

A small Vision Transformer with patch size 16, pretrained on ImageNet-21k with AugReg and fine-tuned on ImageNet-1k for classification.

imagevision

Specs

Context & limits

—

context window

—

max output

Lifecycle

Dates

released2021-10-01

Resources