Pass IndexThe State of AISign in

dinov2-base

Vision Transformer (ViT) model trained using the DINOv2 method.

image → embedding · made by facebook

Sold by

Nobody in the catalogue publishes a price for this yet.

About

dinov2-base — a vectors model from facebook.

It takes images and returns vectors. It was published in July 2023. 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
facebook
Register
model
Takes
image
Returns
embedding
Published
July 2023
Parameters
87 million · read from its own weights
Licence
apache-2.0

Known as 1 name

facebook/dinov2-base