vit-huge-patch14-224-in21k

A Image Features model by google

google 38K downloads unknown Image Features
Frameworkstransformerspytorchtfjaxsafetensors
Datasetsimagenet-21k
PapersarXiv:2010.11929arXiv:2006.03677
Tagsvitimage-feature-extractionvision
Downloads
38K
License
unknown
Pipeline
Image Features
Author
google

Run vit-huge-patch14-224-in21k locally on a Q4KM hard drive

Pre-loaded and ready to run. No download time. No configuration.

Shop Q4KM Drives

Related Image Features Models

F
Image Features
dinov2-small
by facebook
The facebook/dinov2‑small model is a Vision Transformer (ViT) that has been pre‑trained in a...
2.6Mapache-2.0
F
Image Features
dinov2-base
by facebook
The facebook/dinov2-base model is a Hugging Face implementation of a Vision Transformer (ViT‑B/16)...
1.8Mapache-2.0
G
Image Features
vit-base-patch16-224-in21k
by google
The google/vit-base-patch16-224-in21k model is a Vision Transformer (ViT‑Base) that treats an image...
1.1Mapache-2.0
F
Image Features
dinov2-large
by facebook
The facebook/dinov2‑large model is a large‑scale Vision Transformer (ViT) that has been pre‑trained...
639Kapache-2.0

Pre-loaded AI models. Ready to run.

Skip the downloads. Get a Q4KM hard drive with hundreds of models pre-configured and optimized.

Shop Q4KM Hard Drives