LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
Paper • 2104.01136 • Published • 2
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("facebook/levit-256")
model = AutoModelForImageClassification.from_pretrained("facebook/levit-256")Quick Links
LeViT
LeViT-256 model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference by Graham et al. and 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
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 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-256')
model = LevitForImageClassificationWithTeacher.from_pretrained('facebook/levit-256')
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])
- Downloads last month
- 94
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="facebook/levit-256") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")