---
title: levit-128
canonical_url: "https://www.modelscope.cn/models/facebook/levit-128"
md_url: "https://www.modelscope.cn/models/facebook/levit-128.md"
repository: facebook/levit-128
last_updated: 2025-05-20
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
model_type:
  - levit
architectures:
  - LevitForImageClassificationWithTeacher
library_name:
  - transformer
  - pytorch
frameworks:
  - pytorch
downloads: 339
stars: 2
tags:
  - vision
  - image-classification
---

# levit-128

> levit-128 - facebook 在 ModelScope 开源的模型。LeViT-128 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…

facebook/levit-128 是 ModelScope 魔搭社区上的image-classification模型，采用 apache-2.0 许可。

- **Repository**: facebook/levit-128
- **License**: apache-2.0
- **Tasks**: image-classification
- **Tags**: vision, image-classification
- **Downloads**: 339
- **Stars**: 2
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/levit-128

---

# LeViT

LeViT-128 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
](https://arxiv.org/abs/2104.01136) by Graham et al. and first released in [this repository](https://github.com/facebookresearch/LeViT). 

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:

```python
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-128')
model = LevitForImageClassificationWithTeacher.from_pretrained('facebook/levit-128')

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])
```