zeromodels / beit-base-finetuned-ade-640-640

huggingface.co
Total runs: 43
24-hour runs: 4
7-day runs: 5
30-day runs: 42
Model's Last Updated: August 30 2026
image-segmentation

Introduction of beit-base-finetuned-ade-640-640

Model Details of beit-base-finetuned-ade-640-640

See our collection for all versions of BEiT.

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

GitHub Docs Collection

zeromodels/beit-base-finetuned-ade-640-640

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. Base backbone with a UPerNet head fine-tuned on ADE20K (150 classes).

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

Pure- Keras 3 conversion of microsoft/beit-base-finetuned-ade-640-640 for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a semantic segmentation checkpoint ( BeitSemanticSegment ).

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

from PIL import Image
from zeromodels.models.beit import BeitSemanticSegment, BeitImageProcessor

model = BeitSemanticSegment.from_weights("zeromodels/beit-base-finetuned-ade-640-640")
processor = BeitImageProcessor.from_weights("zeromodels/beit-base-finetuned-ade-640-640")  # resize 640 + post-processing

image = Image.open("scene.jpg").convert("RGB")
pixels = processor(image)               # (1, 640, 640, 3), raw [0, 255]; the model normalizes
logits = model(pixels, training=False)  # (1, H/4, W/4, 150), channels_last
seg = processor.post_process_semantic_segmentation(
    logits, target_sizes=[image.size[::-1]]  # (height, width)
)[0]                                     # per-pixel ADE20K label map at full resolution

Load the segmentation checkpoints the same way with from_weights("zeromodels/<variant>") (the classification variants are in the collection ):

Variant Hub Task
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; BeitImageProcessor handles the resize and does not normalize.
  • BeitSemanticSegment returns logits at a quarter of the input resolution. BeitImageProcessor.post_process_semantic_segmentation(logits, target_sizes=[(H, W)]) upsamples them to your image size (bilinear, then argmax) and returns a per-pixel label map.
  • 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. BeitSemanticSegment.from_weights("hf:microsoft/beit-base-finetuned-ade-640-640") .
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-base-finetuned-ade-640-640 on huggingface.co

43
Total runs
4
24-hour runs
4
3-day runs
5
7-day runs
42
30-day runs

More Information About beit-base-finetuned-ade-640-640 huggingface.co Model

More beit-base-finetuned-ade-640-640 license Visit here:

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

beit-base-finetuned-ade-640-640 huggingface.co

beit-base-finetuned-ade-640-640 huggingface.co is an AI model on huggingface.co that provides beit-base-finetuned-ade-640-640's model effect (), which can be used instantly with this zeromodels beit-base-finetuned-ade-640-640 model. huggingface.co supports a free trial of the beit-base-finetuned-ade-640-640 model, and also provides paid use of the beit-base-finetuned-ade-640-640. Support call beit-base-finetuned-ade-640-640 model through api, including Node.js, Python, http.

beit-base-finetuned-ade-640-640 huggingface.co Url

https://huggingface.co/zeromodels/beit-base-finetuned-ade-640-640

zeromodels beit-base-finetuned-ade-640-640 online free

beit-base-finetuned-ade-640-640 huggingface.co is an online trial and call api platform, which integrates beit-base-finetuned-ade-640-640's modeling effects, including api services, and provides a free online trial of beit-base-finetuned-ade-640-640, you can try beit-base-finetuned-ade-640-640 online for free by clicking the link below.

zeromodels beit-base-finetuned-ade-640-640 online free url in huggingface.co:

https://huggingface.co/zeromodels/beit-base-finetuned-ade-640-640

beit-base-finetuned-ade-640-640 install

beit-base-finetuned-ade-640-640 is an open source model from GitHub that offers a free installation service, and any user can find beit-base-finetuned-ade-640-640 on GitHub to install. At the same time, huggingface.co provides the effect of beit-base-finetuned-ade-640-640 install, users can directly use beit-base-finetuned-ade-640-640 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

beit-base-finetuned-ade-640-640 install url in huggingface.co:

https://huggingface.co/zeromodels/beit-base-finetuned-ade-640-640

Url of beit-base-finetuned-ade-640-640

beit-base-finetuned-ade-640-640 huggingface.co Url

Provider of beit-base-finetuned-ade-640-640 huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels