MobileViTv2 (mobilevitv2-1.0-imagenet1k-256)

MobileViTv2 is the second version of MobileViT. It was proposed in Separable Self-attention for Mobile Vision Transformers by Sachin Mehta and Mohammad Rastegari, and first released in this repository. The license used is Apple sample code license.

Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team.

Model Description

MobileViTv2 is constructed by replacing the multi-headed self-attention in MobileViT with separable self-attention.

Intended uses & limitations

You can use the raw model for image classification. See the model hub to look for fine-tuned versions on a task that interests you.

How to use

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 MobileViTImageProcessor, MobileViTV2ForImageClassification
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 = MobileViTImageProcessor.from_pretrained("shehan97/mobilevitv2-1.0-imagenet1k-256")
model = MobileViTV2ForImageClassification.from_pretrained("shehan97/mobilevitv2-1.0-imagenet1k-256")

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])

Currently, both the feature extractor and model support PyTorch.

Training data

The MobileViT model was pretrained on ImageNet-1k, a dataset consisting of 1 million images and 1,000 classes.

BibTeX entry and citation info

@inproceedings{vision-transformer,
title = {Separable Self-attention for Mobile Vision Transformers},
author = {Sachin Mehta and Mohammad Rastegari},
year = {2022},
URL = {https://arxiv.org/abs/2206.02680}
}