A BEiT-3 image classification model. Multimodal model pretrained on ImageNet-22k images, 160GB text documents, and web-scale image-text pairs with masked data modeling. Continued training with in-domain image-text pairs (COCO and Visual Genome). Converted for vision-only classification tasks.

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 303.5
- GMACs: 61.7
- Activations (M): 63.5
- Image size: 224 x 224
Papers:
- BEiT-3: Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks: https://arxiv.org/abs/2208.10442
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
Dataset:
- ImageNet-22k
- Text_documents-160GB
- LAION-400M
- COYO-700M
- CC15M
- COCO
- VG
Original: https://github.com/microsoft/unilm/tree/master/beit3

Model Usage

Image Classification

python

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('beit3_large_patch16_224.indomain_pt', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Feature Map Extraction

python

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'beit3_large_patch16_224.indomain_pt',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 1024, 14, 14])
    #  torch.Size([1, 1024, 14, 14])
    #  torch.Size([1, 1024, 14, 14])

    print(o.shape)

Image Embeddings

python

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'beit3_large_patch16_224.indomain_pt',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 1024) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex

@article{wang2022beit3,
  title={Image as a foreign language: Beit pretraining for vision and vision-language tasks},
  author={Wang, Wenhui and Bao, Hangbo and Dong, Li and Bjorck, Johan and Peng, Zhiliang and Liu, Qiang and Aggarwal, Kriti and Mohammed, Owais Khan and Singhal, Saksham and Som, Subhojit and others},
  journal={arXiv preprint arXiv:2208.10442},
  year={2022}
}

bibtex

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

bibtex

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}

timm/beit3_large_patch16_224.indomain_pt

Model card for beit3_large_patch16_224.indomain_pt

Model Details

Model Usage

Image Classification

Feature Map Extraction

Image Embeddings

Model Comparison

Citation

timm/
beit3_large_patch16_224.indomain_pt