swin-base-patch4-window7-224-in22k

from transformers import AutoImageProcessor, SwinForImageClassification
from PIL import Image
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained("microsoft/swin-base-patch4-window7-224-in22k")
model = SwinForImageClassification.from_pretrained("microsoft/swin-base-patch4-window7-224-in22k")

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

@article{DBLP:journals/corr/abs-2103-14030,
  author    = {Ze Liu and
               Yutong Lin and
               Yue Cao and
               Han Hu and
               Yixuan Wei and
               Zheng Zhang and
               Stephen Lin and
               Baining Guo},
  title     = {Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
  journal   = {CoRR},
  volume    = {abs/2103.14030},
  year      = {2021},
  url       = {https://arxiv.org/abs/2103.14030},
  eprinttype = {arXiv},
  eprint    = {2103.14030},
  timestamp = {Thu, 08 Apr 2021 07:53:26 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2103-14030.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}