Nat Base In1k 224

🚀 NAT (base variant)

NAT (Neighborhood Attention Transformer) is a hierarchical vision transformer for image classification. It was trained on ImageNet - 1K at 224x224 resolution, offering high - performance image classification capabilities.

✨ Features

• Based on Neighborhood Attention (NA), a restricted self - attention pattern that limits each token's receptive field to its nearest neighboring pixels.
• Implemented through the PyTorch extension [NATTEN](https://github.com/SHI - Labs/NATTEN/).
• Highly flexible and maintains translational equivariance due to its sliding - window attention pattern.

📦 Installation

Other than transformers, this model requires the [NATTEN](https://shi - labs.com/natten) package.

• Linux users: You can refer to [shi - labs.com/natten](https://shi - labs.com/natten) for instructions on installing with pre - compiled binaries (just select your torch build to get the correct wheel URL).
• All users: You can alternatively use pip install natten to compile on your device, which may take up to a few minutes. Mac users only have the latter option (no pre - compiled binaries). Refer to [NATTEN's GitHub](https://github.com/SHI - Labs/NATTEN/) for more information.

💻 Usage Examples

Basic Usage

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

from transformers import AutoImageProcessor, NatForImageClassification
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 = AutoImageProcessor.from_pretrained("shi-labs/nat-base-in1k-224")
model = NatForImageClassification.from_pretrained("shi-labs/nat-base-in1k-224")

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 examples, please refer to the documentation.

📚 Documentation

Model description

NAT is a hierarchical vision transformer based on Neighborhood Attention (NA). Neighborhood Attention is a restricted self - attention pattern in which each token's receptive field is limited to its nearest neighboring pixels. NA is a sliding - window attention pattern, and as a result is highly flexible and maintains translational equivariance.

NA is implemented in PyTorch implementations through its extension, [NATTEN](https://github.com/SHI - Labs/NATTEN/).

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{hassani2022neighborhood,
    title        = {Neighborhood Attention Transformer},
    author       = {Ali Hassani and Steven Walton and Jiachen Li and Shen Li and Humphrey Shi},
    year         = 2022,
    url          = {https://arxiv.org/abs/2204.07143},
    eprint       = {2204.07143},
    archiveprefix = {arXiv},
    primaryclass = {cs.CV}
}

📄 License

This project is licensed under the MIT license.