zeromodels / beit-large-patch16-512

huggingface.co
Total runs: 14
24-hour runs: 0
7-day runs: -21
30-day runs: 15
Model's Last Updated: August 30 2026
image-classification

Introduction of beit-large-patch16-512

Model Details of beit-large-patch16-512

See our collection for all versions of BEiT.

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

GitHub Docs Collection

zeromodels/beit-large-patch16-512

Paper: BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254) · HF Papers

BEiT is a ViT-family vision transformer with a per-layer relative position bias, a learnable layer scale on each residual branch, and mean pooling of the patch tokens. Large backbone fine-tuned on ImageNet-1k at 512x512 (1000 classes).

For more details on the model, please go to Microsoft's original model card .

Pure- Keras 3 conversion of microsoft/beit-large-patch16-512 for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a image classification checkpoint ( BeitImageClassify ).

✨ Quick start
import os

os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
from zeromodels.models.beit import BeitImageClassify, BeitModel, BeitImageProcessor

model = BeitImageClassify.from_weights("zeromodels/beit-large-patch16-512")
processor = BeitImageProcessor.from_weights("zeromodels/beit-large-patch16-512")

image = Image.open("your_image.jpg").convert("RGB")
pixels = processor(image)  # resize + normalize (normalization lives in the processor)
logits = model(pixels, training=False)
print(logits.shape)  # (1, num_classes)

# Feature extraction: the backbone without the classifier head
backbone = BeitModel.from_weights("zeromodels/beit-large-patch16-512", as_backbone=True)
features = backbone(pixels, training=False)

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

Variant Hub Task
beit-base-patch16-224 zeromodels/beit-base-patch16-224 image classification
beit-large-patch16-224 zeromodels/beit-large-patch16-224 image classification
beit-large-patch16-512 zeromodels/beit-large-patch16-512 image classification
beit-base-patch16-224-pt22k-ft22k zeromodels/beit-base-patch16-224-pt22k-ft22k image classification
beit-large-patch16-224-pt22k-ft22k zeromodels/beit-large-patch16-224-pt22k-ft22k image classification
beit-base-finetuned-ade-640-640 zeromodels/beit-base-finetuned-ade-640-640 semantic segmentation
beit-large-finetuned-ade-640-640 zeromodels/beit-large-finetuned-ade-640-640 semantic segmentation
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • Normalization (0.5/0.5) is baked into the model, so pass raw [0, 255] pixels.
  • Classification uses BeitImageClassify ; semantic segmentation uses BeitSemanticSegment and returns logits at a quarter of the input resolution (upsample the argmax map to the input size).
  • BeitModel.from_weights(..., as_backbone=True) returns the per-block token sequences for feature extraction.
  • See BEiT docs and Loading Weights .
  • Community / upstream safetensors still work via the hf: prefix, e.g. BeitImageClassify.from_weights("hf:microsoft/beit-large-patch16-512") .
Special Thanks

A huge thank you to the Microsoft Research BEiT authors for creating and releasing these models.

License: Apache 2.0.

Runs of zeromodels beit-large-patch16-512 on huggingface.co

14
Total runs
0
24-hour runs
0
3-day runs
-21
7-day runs
15
30-day runs

More Information About beit-large-patch16-512 huggingface.co Model

More beit-large-patch16-512 license Visit here:

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

beit-large-patch16-512 huggingface.co

beit-large-patch16-512 huggingface.co is an AI model on huggingface.co that provides beit-large-patch16-512's model effect (), which can be used instantly with this zeromodels beit-large-patch16-512 model. huggingface.co supports a free trial of the beit-large-patch16-512 model, and also provides paid use of the beit-large-patch16-512. Support call beit-large-patch16-512 model through api, including Node.js, Python, http.

beit-large-patch16-512 huggingface.co Url

https://huggingface.co/zeromodels/beit-large-patch16-512

zeromodels beit-large-patch16-512 online free

beit-large-patch16-512 huggingface.co is an online trial and call api platform, which integrates beit-large-patch16-512's modeling effects, including api services, and provides a free online trial of beit-large-patch16-512, you can try beit-large-patch16-512 online for free by clicking the link below.

zeromodels beit-large-patch16-512 online free url in huggingface.co:

https://huggingface.co/zeromodels/beit-large-patch16-512

beit-large-patch16-512 install

beit-large-patch16-512 is an open source model from GitHub that offers a free installation service, and any user can find beit-large-patch16-512 on GitHub to install. At the same time, huggingface.co provides the effect of beit-large-patch16-512 install, users can directly use beit-large-patch16-512 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

beit-large-patch16-512 install url in huggingface.co:

https://huggingface.co/zeromodels/beit-large-patch16-512

Url of beit-large-patch16-512

beit-large-patch16-512 huggingface.co Url

Provider of beit-large-patch16-512 huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels