Introduction of beitv2_base_patch16_224.in1k_ft_in22k
Model Details of beitv2_base_patch16_224.in1k_ft_in22k
Model card for beitv2_base_patch16_224.in1k_ft_in22k
A BEiT-v2 image classification model. Trained on ImageNet-1k with self-supervised masked image modelling (MIM) using a VQ-KD encoder as a visual tokenizer (via OpenAI CLIP B/16 teacher). Fine-tuned on ImageNet-22k.
Model Details
Model Type:
Image classification / feature backbone
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('beitv2_base_patch16_224.in1k_ft_in22k', 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)
Image Embeddings
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(
'beitv2_base_patch16_224.in1k_ft_in22k',
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, 768) 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
@article{peng2022beit,
title={Beit v2: Masked image modeling with vector-quantized visual tokenizers},
author={Peng, Zhiliang and Dong, Li and Bao, Hangbo and Ye, Qixiang and Wei, Furu},
journal={arXiv preprint arXiv:2208.06366},
year={2022}
}
@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}
}
@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}}
}
Runs of timm beitv2_base_patch16_224.in1k_ft_in22k on huggingface.co
136.6K
Total runs
0
24-hour runs
-2.4K
3-day runs
-6.9K
7-day runs
15.3K
30-day runs
More Information About beitv2_base_patch16_224.in1k_ft_in22k huggingface.co Model
More beitv2_base_patch16_224.in1k_ft_in22k license Visit here:
beitv2_base_patch16_224.in1k_ft_in22k huggingface.co is an AI model on huggingface.co that provides beitv2_base_patch16_224.in1k_ft_in22k's model effect (), which can be used instantly with this timm beitv2_base_patch16_224.in1k_ft_in22k model. huggingface.co supports a free trial of the beitv2_base_patch16_224.in1k_ft_in22k model, and also provides paid use of the beitv2_base_patch16_224.in1k_ft_in22k. Support call beitv2_base_patch16_224.in1k_ft_in22k model through api, including Node.js, Python, http.
beitv2_base_patch16_224.in1k_ft_in22k huggingface.co is an online trial and call api platform, which integrates beitv2_base_patch16_224.in1k_ft_in22k's modeling effects, including api services, and provides a free online trial of beitv2_base_patch16_224.in1k_ft_in22k, you can try beitv2_base_patch16_224.in1k_ft_in22k online for free by clicking the link below.
timm beitv2_base_patch16_224.in1k_ft_in22k online free url in huggingface.co:
beitv2_base_patch16_224.in1k_ft_in22k is an open source model from GitHub that offers a free installation service, and any user can find beitv2_base_patch16_224.in1k_ft_in22k on GitHub to install. At the same time, huggingface.co provides the effect of beitv2_base_patch16_224.in1k_ft_in22k install, users can directly use beitv2_base_patch16_224.in1k_ft_in22k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
beitv2_base_patch16_224.in1k_ft_in22k install url in huggingface.co: