Levit 128

🚀 LeViT

The LeViT-128 model is pre-trained on ImageNet-1k at a resolution of 224x224. It offers efficient image classification capabilities, leveraging the advantages of both vision transformers and convolutional networks.

🚀 Quick Start

The LeViT-128 model was introduced in the paper LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference by Graham et al. and was first released in this repository.

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

💻 Usage Examples

Basic Usage

from transformers import LevitFeatureExtractor, LevitForImageClassificationWithTeacher
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 = LevitFeatureExtractor.from_pretrained('facebook/levit-128')
model = LevitForImageClassificationWithTeacher.from_pretrained('facebook/levit-128')

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])

📄 License

This model is licensed under the Apache-2.0 license.