zeromodels / dino-vitb16

huggingface.co
Total runs: 18
24-hour runs: 0
7-day runs: -4
30-day runs: -4
Model's Last Updated: August 27 2026
image-feature-extraction

Introduction of dino-vitb16

Model Details of dino-vitb16

See our collection for all versions of DINO.

Run DINO with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Docs Collection

zeromodels/dino-vitb16

Paper: Emerging Properties in Self-Supervised Vision Transformers (arXiv:2104.14294) · HF Papers

DINO is self-supervised: a student and teacher match across crops of the same image with no labels. The resulting features are semantic for free. These checkpoints are backbones that return tokens / feature maps.

For more details on the model, please go to the upstream model card .

Pure- Keras 3 conversion of facebook/dino-vitb16 for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a self-supervised backbone ( DinoViTModel ), not a task head.

✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from zeromodels.models.dino import DinoViTModel, DinoImageProcessor

# The processor resizes + ImageNet-normalizes, so build the model with
# include_normalization=False (it would otherwise normalize a second time).
model = DinoViTModel.from_weights(
    "zeromodels/dino-vitb16", include_normalization=False
)
processor = DinoImageProcessor.from_weights("zeromodels/dino-vitb16")

pixel_values = processor("your_image.jpg")["pixel_values"]
features = model(pixel_values, training=False)
print(pixel_values.shape, features.shape)

Load any DINO variant the same way with from_weights("zeromodels/<variant>") :

Variant Hub Backbone
dino-vits16 zeromodels/dino-vits16 ViT-S/16
dino-vits8 zeromodels/dino-vits8 ViT-S/8
dino-vitb16 zeromodels/dino-vitb16 ViT-B/16
dino-vitb8 zeromodels/dino-vitb8 ViT-B/8
dino-resnet50 zeromodels/dino-resnet50 ResNet-50
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • The processor normalizes; pair it with include_normalization=False . To skip it, feed raw [0, 255] pixels and keep the default include_normalization=True .
  • dino-resnet50 was converted from torch.hub facebookresearch/dino .
  • See DINO docs and Loading Weights .
  • Community / upstream weights: DinoViTModel.from_weights("hf:facebook/dino-vitb16") .
Special Thanks

A huge thank you to the Facebook AI Research DINO authors for creating and releasing these models.

License: Apache 2.0.

Runs of zeromodels dino-vitb16 on huggingface.co

18
Total runs
0
24-hour runs
1
3-day runs
-4
7-day runs
-4
30-day runs

More Information About dino-vitb16 huggingface.co Model

More dino-vitb16 license Visit here:

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

dino-vitb16 huggingface.co

dino-vitb16 huggingface.co is an AI model on huggingface.co that provides dino-vitb16's model effect (), which can be used instantly with this zeromodels dino-vitb16 model. huggingface.co supports a free trial of the dino-vitb16 model, and also provides paid use of the dino-vitb16. Support call dino-vitb16 model through api, including Node.js, Python, http.

zeromodels dino-vitb16 online free

dino-vitb16 huggingface.co is an online trial and call api platform, which integrates dino-vitb16's modeling effects, including api services, and provides a free online trial of dino-vitb16, you can try dino-vitb16 online for free by clicking the link below.

zeromodels dino-vitb16 online free url in huggingface.co:

https://huggingface.co/zeromodels/dino-vitb16

dino-vitb16 install

dino-vitb16 is an open source model from GitHub that offers a free installation service, and any user can find dino-vitb16 on GitHub to install. At the same time, huggingface.co provides the effect of dino-vitb16 install, users can directly use dino-vitb16 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

dino-vitb16 install url in huggingface.co:

https://huggingface.co/zeromodels/dino-vitb16

Url of dino-vitb16

Provider of dino-vitb16 huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels