AI說書 - 從0開始 - 564 | ViT-base-patch16-224 ImageClassification

我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。

image_path=”/content/car_in_fog.png”
import PIL 
image = PIL.Image.open(image_path)

from transformers import ViTFeatureExtractor, ViTForImageClassification 
from PIL import Image 
import requests

feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224') 
model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')

inputs = feature_extractor(images = image, return_tensors = "pt")
outputs = model(**inputs) 
logits = outputs.logits

predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:",predicted_class_idx,": ", model.config. id2label[predicted_class_idx])

結果為：