Rope Vit Reg4 B14 Capi Imagenet21k

🚀 Model Card for rope_vit_reg4_b14_capi-imagenet21k

A RoPE ViT image classification model that undergoes a two - stage training process: first CAPI pretraining, then fine - tuning on the ImageNet - 21K dataset.

🚀 Quick Start

This is a RoPE ViT image classification model. It follows a two - stage training process: first, it goes through CAPI pretraining, and then it is fine - tuned on the ImageNet-21K dataset.

✨ Features

RoPE Configuration

This model implements EVA - style Rotary Position Embedding (RoPE). When working with resolutions different from the training resolution (224x224), the model behavior can be optimized by configuring the pt_grid_size parameter:

• For inference at higher resolutions or when performing "shallow" fine - tuning, it's recommended to explicitly set pt_grid_size=(16, 16) (the default grid size during pretraining).
• For aggressive fine - tuning at higher resolutions, leave pt_grid_size as None to allow the model to adapt to the new resolution.

Setting pt_grid_size during inference:

# When running inference with a custom resolution (e.g., 336x336)
python predict.py --network rope_vit_reg4_b14 -t capi-imagenet21k --model-config '{"pt_grid_size":[16, 16]}' --size 336 ...

Converting the model with explicit RoPE configuration:

python tool.py convert-model --network rope_vit_reg4_b14 -t capi-imagenet21k --add-config '{"pt_grid_size":[16, 16]}'

📚 Documentation

Model Details

💻 Usage Examples

Basic Usage - Image Classification

import birder
from birder.inference.classification import infer_image

(net, model_info) = birder.load_pretrained_model("rope_vit_reg4_b14_capi-imagenet21k", inference=True)

# Get the image size the model was trained on
size = birder.get_size_from_signature(model_info.signature)

# Create an inference transform
transform = birder.classification_transform(size, model_info.rgb_stats)

image = "path/to/image.jpeg"  # or a PIL image, must be loaded in RGB format
(out, _) = infer_image(net, image, transform)
# out is a NumPy array with shape of (1, 19167), representing class probabilities.

Advanced Usage - Image Embeddings

import birder
from birder.inference.classification import infer_image

(net, model_info) = birder.load_pretrained_model("rope_vit_reg4_b14_capi-imagenet21k", inference=True)

# Get the image size the model was trained on
size = birder.get_size_from_signature(model_info.signature)

# Create an inference transform
transform = birder.classification_transform(size, model_info.rgb_stats)

image = "path/to/image.jpeg"  # or a PIL image
(out, embedding) = infer_image(net, image, transform, return_embedding=True)
# embedding is a NumPy array with shape of (1, 768)

Advanced Usage - Detection Feature Map

from PIL import Image
import birder

(net, model_info) = birder.load_pretrained_model("rope_vit_reg4_b14_capi-imagenet21k", inference=True)

# Get the image size the model was trained on
size = birder.get_size_from_signature(model_info.signature)

# Create an inference transform
transform = birder.classification_transform(size, model_info.rgb_stats)

image = Image.open("path/to/image.jpeg")
features = net.detection_features(transform(image).unsqueeze(0))
# features is a dict (stage name -> torch.Tensor)
print([(k, v.size()) for k, v in features.items()])
# Output example:
# [('neck', torch.Size([1, 768, 16, 16]))]

📄 License

This model is licensed under the apache-2.0 license.

📄 Citation

@misc{dosovitskiy2021imageworth16x16words,
      title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, 
      author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
      year={2021},
      eprint={2010.11929},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2010.11929}, 
}

@misc{heo2024rotarypositionembeddingvision,
      title={Rotary Position Embedding for Vision Transformer},
      author={Byeongho Heo and Song Park and Dongyoon Han and Sangdoo Yun},
      year={2024},
      eprint={2403.13298},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2403.13298},
}

@misc{darcet2024visiontransformersneedregisters,
      title={Vision Transformers Need Registers}, 
      author={Timothée Darcet and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
      year={2024},
      eprint={2309.16588},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2309.16588}, 
}

@misc{darcet2025clusterpredictlatentpatches,
      title={Cluster and Predict Latent Patches for Improved Masked Image Modeling},
      author={Timothée Darcet and Federico Baldassarre and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
      year={2025},
      eprint={2502.08769},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2502.08769},
}