Transformers vit image model vector acquisition

Reference resources ：https://huggingface.co/facebook/dino-vitb16

**** last_hidden_states 197 individual token; This is a 1616 Divide picture 224224, The latter is divided apart from the former 196 individual patch, Add one more transformer The first one added cls token, common 197 individual

from transformers import ViTFeatureExtractor, ViTModel
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 = ViTFeatureExtractor.from_pretrained('facebook/dino-vitb16')
model = ViTModel.from_pretrained('facebook/dino-vitb16')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state

*** To obtain cls token Vector embedding