Beit Large Patch16 224 Pt22k

🚀 BEiT (large-sized model, pre-trained only)

BEiT is a model pre-trained in a self-supervised manner on ImageNet-22k (also known as ImageNet-21k, which contains 14 million images and 21,841 classes) at a resolution of 224x224. It was introduced in the paper BEIT: BERT Pre-Training of Image Transformers by Hangbo Bao, Li Dong, and Furu Wei, and first released in this repository.

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

✨ Features

• BEiT is a Vision Transformer (ViT), a transformer encoder model similar to BERT.
• It is pre-trained on a large collection of images (ImageNet-21k) in a self-supervised fashion at 224x224 resolution.
• It uses relative position embeddings (similar to T5) instead of absolute position embeddings.
• It classifies images by mean-pooling the final hidden states of patches.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import BeitFeatureExtractor, BeitForMaskedImageModeling
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 = BeitFeatureExtractor.from_pretrained('microsoft/beit-large-patch16-224-pt22k')
model = BeitForMaskedImageModeling.from_pretrained('microsoft/beit-large-patch16-224-pt22k')

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

Currently, both the feature extractor and model support PyTorch.

📚 Documentation

Model description

The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT is pretrained on a large collection of images in a self-supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. The pre-training objective for the model is to predict visual tokens from the encoder of OpenAI's DALL-E's VQ-VAE, based on masked patches.

Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. Contrary to the original ViT models, BEiT models do use relative position embeddings (similar to T5) instead of absolute position embeddings, and perform classification of images by mean-pooling the final hidden states of the patches, instead of placing a linear layer on top of the final hidden state of the [CLS] token.

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. Alternatively, one can mean-pool the final hidden states of the patch embeddings, and place a linear layer on top of that.

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 BEiT 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

For all pre-training related hyperparameters, we refer to page 15 of the original paper.

Evaluation results

For evaluation results on several image classification benchmarks, we refer to tables 1 and 2 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution. Of course, increasing the model size will result in better performance.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2106-08254,
  author    = {Hangbo Bao and
               Li Dong and
               Furu Wei},
  title     = {BEiT: {BERT} Pre-Training of Image Transformers},
  journal   = {CoRR},
  volume    = {abs/2106.08254},
  year      = {2021},
  url       = {https://arxiv.org/abs/2106.08254},
  archivePrefix = {arXiv},
  eprint    = {2106.08254},
  timestamp = {Tue, 29 Jun 2021 16:55:04 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2106-08254.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@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}
}

📄 License

This model is licensed under the Apache-2.0 license.