An open-weight Vision Transformer model for image classification, trained on ImageNet-21k and fine-tuned on ImageNet-1k. It can be loaded locally with timm or Transformers for inference and model development.
In the Other AI space, Vit Base Patch8 224.augreg2 In21k Ft In1k takes a focused approach. It focuses on running a pretrained Vision Transformer locally for image classification without training a model from scratch. Vit Base Patch8 224.augreg2 In21k Ft In1k is an open-source project aimed at machine learning developers and computer vision researchers. Vit Base Patch8 224.augreg2 In21k Ft In1k is open source under the Apache-2.0 license. Vit Base Patch8 224.augreg2 In21k Ft In1k is available on the web and the command line, and it can be self-hosted.
It is developed by PyTorch Image Models, and it first shipped in 2020. Development happens publicly on GitHub with 12.7k stars and 2 commits in the last 90 days. Among its 6 catalogued features are image classification, imageNet training, and pyTorch support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do