convnextv2-atto-1k-224

from transformers import AutoImageProcessor, ConvNextV2ForImageClassification
import torch
from datasets import load_dataset

dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]

preprocessor = AutoImageProcessor.from_pretrained("facebook/convnextv2-atto-1k-224")
model = ConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-atto-1k-224")

inputs = preprocessor(image, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label]),

@article{DBLP:journals/corr/abs-2301-00808,
  author    = {Sanghyun Woo and
               Shoubhik Debnath and
               Ronghang Hu and
               Xinlei Chen and
               Zhuang Liu and
               In So Kweon and
               Saining Xie},
  title     = {ConvNeXt {V2:} Co-designing and Scaling ConvNets with Masked Autoencoders},
  journal   = {CoRR},
  volume    = {abs/2301.00808},
  year      = {2023},
  url       = {https://doi.org/10.48550/arXiv.2301.00808},
  doi       = {10.48550/arXiv.2301.00808},
  eprinttype = {arXiv},
  eprint    = {2301.00808},
  timestamp = {Tue, 10 Jan 2023 15:10:12 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2301-00808.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}