Swin Large Patch4 Window7 224 In22k

🚀 Swin Transformer (large-sized model)

The Swin Transformer is a pre - trained model on ImageNet - 21k (14 million images, 21,841 classes) at a resolution of 224x224. It offers an effective solution for image classification and dense recognition tasks by leveraging hierarchical feature maps and local self - attention mechanisms.

🚀 Quick Start

The Swin Transformer model, pre - trained on ImageNet - 21k, can be used for image classification tasks. You can find fine - tuned versions on the model hub according to your needs.

✨ Features

• Hierarchical Feature Maps: The Swin Transformer builds hierarchical feature maps by merging image patches in deeper layers, which is beneficial for various computer vision tasks.
• Linear Computation Complexity: It has linear computation complexity to the input image size because self - attention is computed only within each local window, making it more efficient for large - scale images compared to previous vision Transformers.

📚 Documentation

Model description

The Swin Transformer is a type of Vision Transformer. It builds hierarchical feature maps by merging image patches (shown in gray) in deeper layers and has linear computation complexity to input image size due to computation of self - attention only within each local window (shown in red). It can thus serve as a general - purpose backbone for both image classification and dense recognition tasks. In contrast, previous vision Transformers produce feature maps of a single low resolution and have quadratic computation complexity to input image size due to computation of self - attention globally.

Source

Intended uses & limitations

You can use the raw model for image classification. See the model hub to look for fine - tuned versions on a task that interests you.

💻 Usage Examples

Basic Usage

Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:

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

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

feature_extractor = AutoFeatureExtractor.from_pretrained("microsoft/swin-large-patch4-window7-224-in22k")
model = SwinForImageClassification.from_pretrained("microsoft/swin-large-patch4-window7-224-in22k")

inputs = feature_extractor(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])

For more code examples, we refer to the documentation.

📄 License

This model is released under the Apache - 2.0 license.

BibTeX entry and citation info

@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}
}