Swinv2 Base Patch4 Window16 256

🚀 Swin Transformer v2 (base-sized model)

A pre - trained Swin Transformer v2 model on ImageNet - 1k at 256x256 resolution, offering advanced image classification capabilities.

✨ Features

• Hierarchical Feature Maps: Builds hierarchical feature maps by merging image patches in deeper layers.
• Linear Computation Complexity: Has linear computation complexity to input image size due to local self - attention computation.
• General - Purpose Backbone: Can serve as a backbone for both image classification and dense recognition tasks.
• Improved Training Stability: Swin Transformer v2 uses a residual - post - norm method combined with cosine attention.
• Effective Transfer Learning: Employs a log - spaced continuous position bias method for better transfer to high - resolution tasks.
• Reduced Label Dependency: Utilizes a self - supervised pre - training method, SimMIM, to reduce the need for vast labeled images.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

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-window16-256")
model = AutoModelForImageClassification.from_pretrained("microsoft/swinv2-base-patch4-window16-256")

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])

Advanced Usage

For more code examples, we refer to the documentation.

📚 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.

Swin Transformer v2 adds 3 main improvements: 1) a residual - post - norm method combined with cosine attention to improve training stability; 2) a log - spaced continuous position bias method to effectively transfer models pre - trained using low - resolution images to downstream tasks with high - resolution inputs; 3) a self - supervised pre - training method, SimMIM, to reduce the needs of vast labeled images.

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.

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}
}

🔧 Technical Details

The Swin Transformer's unique architecture allows it to build hierarchical feature maps and have linear computation complexity. Swin Transformer v2 further enhances the model with improvements in training stability, transfer learning, and reducing the need for labeled data.

📄 License

The model is licensed under the Apache 2.0 license.