Swinv2 Base Patch4 Window12 192 22k

🚀 Swin Transformer v2 (tiny-sized model)

Swin Transformer v2 is a pre - trained model on ImageNet - 21k at 192x192 resolution. It offers a hierarchical feature map construction and linear computation complexity for image - related tasks.

🚀 Quick Start

The Swin Transformer v2 model presented here is pre - trained on ImageNet - 21k at a resolution of 192x192. It was introduced in the paper Swin Transformer V2: Scaling Up Capacity and Resolution by Liu et al. and first released in [this repository](https://github.com/microsoft/Swin - Transformer).

Disclaimer: The team releasing Swin Transformer v2 did not write a model card for this model, so this model card has been written by the Hugging Face team.

✨ Features

Model description

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

Swin Transformer v2 brings 3 main improvements:

1. A residual - post - norm method combined with cosine attention to enhance training stability.
2. A log - spaced continuous position bias method to effectively transfer models pre - trained on low - resolution images to downstream tasks with high - resolution inputs.
3. A self - supervised pre - training method, SimMIM, to reduce the need for a large number of labeled images.

[Source](https://paperswithcode.com/method/swin - transformer)

Intended uses & limitations

You can utilize the raw model for image classification. Check out the model hub to find fine - tuned versions for tasks that interest you.

💻 Usage Examples

Basic Usage

Here is how to use this model to classify an image from the COCO 2017 dataset into one of the 21k ImageNet classes:

from transformers import AutoImageProcessor, AutoModelForImageClassification
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/swinv2-base-patch4-window12-192-22k")
model = AutoModelForImageClassification.from_pretrained("microsoft/swinv2-base-patch4-window12-192-22k")

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 21k ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

For more code examples, refer to the documentation.

📚 Documentation

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2111-09883,
  author    = {Ze Liu and
               Han Hu and
               Yutong Lin and
               Zhuliang Yao and
               Zhenda Xie and
               Yixuan Wei and
               Jia Ning and
               Yue Cao and
               Zheng Zhang and
               Li Dong and
               Furu Wei and
               Baining Guo},
  title     = {Swin Transformer {V2:} Scaling Up Capacity and Resolution},
  journal   = {CoRR},
  volume    = {abs/2111.09883},
  year      = {2021},
  url       = {https://arxiv.org/abs/2111.09883},
  eprinttype = {arXiv},
  eprint    = {2111.09883},
  timestamp = {Thu, 02 Dec 2021 15:54:22 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2111-09883.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

📄 License

This model is licensed under the Apache - 2.0 license.