Pass IndexThe State of AISign in

vit-base-patch16-224-in21k

Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224.

image → embedding · made by Google

Sold by

Nobody in the catalogue publishes a price for this yet.

About

vit-base-patch16-224-in21k — a vectors model from Google.

It takes images and returns vectors. It was published in March 2022. The catalogue files it under embedding. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
Google
Register
model
Takes
image
Returns
embedding
Published
March 2022
Parameters
86 million · read from its own weights
Licence
apache-2.0

Known as 1 name

google/vit-base-patch16-224-in21k