Convolutional Vision Transformer (CvT)

CvT-13 model pre-trained on ImageNet-22k and fine-tuned on ImageNet-1k at resolution 384x384. It was introduced in the paper CvT: Introducing Convolutions to Vision Transformers by Wu et al. and first released in this repository .

Disclaimer: The team releasing CvT 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 AutoFeatureExtractor, CvtForImageClassification
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 = AutoFeatureExtractor.from_pretrained('microsoft/cvt-13-384-22k')
model = CvtForImageClassification.from_pretrained('microsoft/cvt-13-384-22k')

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])