timm / vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

huggingface.co
Total runs: 44.5K
24-hour runs: 0
7-day runs: 879
30-day runs: 43.8K
Model's Last Updated: January 21 2025
image-classification

Introduction of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

Model Details of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

Model card for vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

A Vision Transformer (ViT) image classification model. This is a timm specific variation of the architecture with registers, global average pooling.

There are a number of models in the lower end of model scales that originate in timm :

variant width mlp width (mult) heads depth timm orig
tiny 192 768 (4) 3 12 n
wee 256 1280 (5) 4 14 y
pwee 256 1280 (5) 4 16 (parallel) y
small 384 1536 (4) 6 12 n
little 320 1792 (5.6) 5 14 y
medium 512 2048 (4) 8 12 y
mediumd 512 2048 (4) 8 20 y
betwixt 640 2560 (4) 10 12 y
base 768 3072 (4) 12 12 n

Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in timm using recipe template described below.

Recipe details:

  • Searching for better baselines. Influced by Swin/DeiT/DeiT-III but w/ increased weight decay, moderate (in12k) to high (in1k) augmentation. Layer-decay used for fine-tune. Some runs used BCE and/or NAdamW instead of AdamW.
  • See train_hparams.yaml for specifics of each model.
Model Details
Model Usage
Image Classification
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('vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k', 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
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(
    'vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k',
    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, 512, 24, 24])
    #  torch.Size([1, 512, 24, 24])
    #  torch.Size([1, 512, 24, 24])

    print(o.shape)
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(
    'vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k',
    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, 580, 512) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Model Comparison
model top1 top5 param_count img_size
vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k 87.438 98.256 64.11 384
vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k 86.608 97.934 64.11 256
vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k 86.594 98.02 60.4 384
vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k 86.202 97.874 64.11 256
vit_betwixt_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k 85.734 97.61 60.4 256
vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k 85.418 97.480 60.4 256
vit_medium_patch16_reg4_gap_256.sbb_in12k_ft_in1k 84.930 97.386 38.88 256
vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k 84.322 96.812 63.95 256
vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k 83.906 96.684 60.23 256
vit_base_patch16_rope_reg1_gap_256.sbb_in1k 83.866 96.67 86.43 256
vit_medium_patch16_rope_reg1_gap_256.sbb_in1k 83.81 96.824 38.74 256
vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k 83.774 96.972 22.52 256
vit_betwixt_patch16_reg4_gap_256.sbb_in1k 83.706 96.616 60.4 256
vit_betwixt_patch16_reg1_gap_256.sbb_in1k 83.628 96.544 60.4 256
vit_medium_patch16_reg4_gap_256.sbb_in1k 83.47 96.622 38.88 256
vit_medium_patch16_reg1_gap_256.sbb_in1k 83.462 96.548 38.88 256
vit_little_patch16_reg4_gap_256.sbb_in1k 82.514 96.262 22.52 256
vit_wee_patch16_reg1_gap_256.sbb_in1k 80.258 95.360 13.42 256
vit_pwee_patch16_reg1_gap_256.sbb_in1k 80.072 95.136 15.25 256
Citation
@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}}
}
@article{darcet2023vision,
  title={Vision Transformers Need Registers},
  author={Darcet, Timoth{'e}e and Oquab, Maxime and Mairal, Julien and Bojanowski, Piotr},
  journal={arXiv preprint arXiv:2309.16588},
  year={2023}
}
@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}
}

Runs of timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k on huggingface.co

44.5K
Total runs
0
24-hour runs
359
3-day runs
879
7-day runs
43.8K
30-day runs

More Information About vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co Model

More vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k license Visit here:

https://choosealicense.com/licenses/apache-2.0

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co is an AI model on huggingface.co that provides vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k's model effect (), which can be used instantly with this timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k model. huggingface.co supports a free trial of the vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k model, and also provides paid use of the vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k. Support call vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k model through api, including Node.js, Python, http.

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co Url

https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k online free

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co is an online trial and call api platform, which integrates vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k's modeling effects, including api services, and provides a free online trial of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k, you can try vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k online for free by clicking the link below.

timm vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k online free url in huggingface.co:

https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k install

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k is an open source model from GitHub that offers a free installation service, and any user can find vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k on GitHub to install. At the same time, huggingface.co provides the effect of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k install, users can directly use vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k install url in huggingface.co:

https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

Url of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k

vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co Url

Provider of vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k huggingface.co

timm
ORGANIZATIONS

Other API from timm

huggingface.co

Total runs: 19.0M
Run Growth: -1.8M
Growth Rate: -9.67%
Updated: January 21 2025
huggingface.co

Total runs: 4.9M
Run Growth: 3.3M
Growth Rate: 68.60%
Updated: January 21 2025
huggingface.co

Total runs: 125.5K
Run Growth: 103.6K
Growth Rate: 82.60%
Updated: October 25 2023
huggingface.co

Total runs: 121.9K
Run Growth: -120.0K
Growth Rate: -98.99%
Updated: January 21 2025
huggingface.co

Total runs: 113.9K
Run Growth: -112.3K
Growth Rate: -100.13%
Updated: January 21 2025
huggingface.co

Total runs: 112.5K
Run Growth: 101.7K
Growth Rate: 89.79%
Updated: January 21 2025
huggingface.co

Total runs: 90.3K
Run Growth: 64.4K
Growth Rate: 80.38%
Updated: January 21 2025
huggingface.co

Total runs: 31.4K
Run Growth: 8.7K
Growth Rate: 27.99%
Updated: January 21 2025
huggingface.co

Total runs: 24.0K
Run Growth: 7.5K
Growth Rate: 31.41%
Updated: January 21 2025
huggingface.co

Total runs: 22.4K
Run Growth: 15.1K
Growth Rate: 70.96%
Updated: January 21 2025
huggingface.co

Total runs: 20.8K
Run Growth: 6.5K
Growth Rate: 32.11%
Updated: January 21 2025
huggingface.co

Total runs: 20.5K
Run Growth: 6.0K
Growth Rate: 30.02%
Updated: January 21 2025
huggingface.co

Total runs: 20.5K
Run Growth: 5.8K
Growth Rate: 28.79%
Updated: January 21 2025
huggingface.co

Total runs: 20.2K
Run Growth: 15.2K
Growth Rate: 76.29%
Updated: January 21 2025