Vit Large Patch32 224 In21k

🚀 Vision Transformer (large-sized model)

A Vision Transformer (ViT) model pre-trained on ImageNet-21k for image representation learning.

🚀 Quick Start

The Vision Transformer (ViT) is pre-trained on ImageNet-21k (14 million images, 21,843 classes) at a resolution of 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository.

✨ Features

• Transformer-based: Utilizes a transformer encoder architecture for image processing.
• Pre-trained on large dataset: Trained on ImageNet-21k to learn rich image representations.
• Useful for downstream tasks: Can be used for various image-related tasks like classification.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

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('google/vit-base-patch16-224-in21k')
model = ViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_state = outputs.last_hidden_state

Note that currently, both the feature extractor and model support PyTorch. Tensorflow and JAX/FLAX are coming soon, and the API of ViTFeatureExtractor might change.

📚 Documentation

Model description

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels.

Images are presented to the model as a sequence of fixed-size patches (resolution 32x32), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.

Note that this model does not provide any fine-tuned heads, as these were zero'd by Google researchers. However, the model does include the pre-trained pooler, which can be used for downstream tasks (such as image classification).

By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.

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.

Training data

The ViT model was pretrained on ImageNet-21k, a dataset consisting of 14 million images and 21k classes.

Training procedure

Preprocessing

The exact details of preprocessing of images during training/validation can be found here.

Images are resized/rescaled to the same resolution (224x224) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).

Pretraining

The model was trained on TPUv3 hardware (8 cores). All model variants are trained with a batch size of 4096 and learning rate warmup of 10k steps. For ImageNet, the authors found it beneficial to additionally apply gradient clipping at global norm 1. Pre-training resolution is 224.

Evaluation results

For evaluation results on several image classification benchmarks, we refer to tables 2 and 5 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution (384x384). Of course, increasing the model size will result in better performance.

🔧 Technical Details

• Model Type: Vision Transformer (ViT)
• Training Data: ImageNet-21k

📄 License

This model is licensed under the Apache-2.0 license.

BibTeX entry and citation info

@misc{wu2020visual,
      title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision}, 
      author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
      year={2020},
      eprint={2006.03677},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@inproceedings{deng2009imagenet,
  title={Imagenet: A large-scale hierarchical image database},
  author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
  booktitle={2009 IEEE conference on computer vision and pattern recognition},
  pages={248--255},
  year={2009},
  organization={Ieee}
}