LeViT

LeViT-384 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-384')
model = LevitForImageClassificationWithTeacher.from_pretrained('facebook/levit-384')

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])

LeViT

LeViT-384 模型在 ImageNet-1k 上以 224x224 的分辨率进行预训练。它由 Graham 等人于 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference 年发表，并在 this repository 年首次发布。

免责声明：LeViT 团队未为此模型编写模型卡片，因此此模型卡片由 Hugging Face 团队编写。

用法

以下是如何使用该模型将 COCO 2017 数据集的图像分类为 1,000 个 ImageNet 类别的方法：

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-384')
model = LevitForImageClassificationWithTeacher.from_pretrained('facebook/levit-384')

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])