zeromodels / oneformer_cityscapes_swin_large

huggingface.co
Total runs: 32
24-hour runs: -1
7-day runs: -10
30-day runs: -1
Model's Last Updated: August 27 2026
image-segmentation

Introduction of oneformer_cityscapes_swin_large

Model Details of oneformer_cityscapes_swin_large

See our collection for all versions of OneFormer.

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

GitHub Docs Collection

zeromodels/oneformer_cityscapes_swin_large

Paper: OneFormer: One Transformer to Rule Universal Image Segmentation (arXiv:2211.06220) · HF Papers

OneFormer trains one model on semantic, instance, and panoptic segmentation jointly, conditioned on a text token that names the task. At inference you pass task="semantic" , "instance" , or "panoptic" to the same weights. The processor combines an image processor and a tokenizer for that task token.

For more details on the model, please go to SHI Labs' original model card .

Pure- Keras 3 conversion of shi-labs/oneformer_cityscapes_swin_large for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a universal segmentation checkpoint ( OneFormerUniversalSegment ) trained on Cityscapes (19 classes, Swin-Large). All three tasks share these weights.

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

from PIL import Image
from zeromodels.models.oneformer import (
    OneFormerUniversalSegment,
    OneFormerProcessor,
)

model = OneFormerUniversalSegment.from_weights("zeromodels/oneformer_cityscapes_swin_large")
processor = OneFormerProcessor.from_weights("zeromodels/oneformer_cityscapes_swin_large")

image = Image.open("your_image.jpg").convert("RGB")
# task is an argument: "semantic" | "instance" | "panoptic"
inputs = processor(images=image, task="panoptic")
output = model(inputs)
result = processor.post_process_panoptic_segmentation(
    output, target_size=(image.height, image.width)
)
print(result["segmentation"].shape)

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

Variant Hub Dataset Backbone
oneformer_ade20k_swin_tiny zeromodels/oneformer_ade20k_swin_tiny ADE20K Swin-Tiny
oneformer_ade20k_swin_large zeromodels/oneformer_ade20k_swin_large ADE20K Swin-Large
oneformer_coco_swin_large zeromodels/oneformer_coco_swin_large COCO Swin-Large
oneformer_cityscapes_swin_large zeromodels/oneformer_cityscapes_swin_large Cityscapes Swin-Large
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • Prefer OneFormerProcessor.from_weights(...) so image size and tokenizer match the variant.
  • Pick the task at call time via processor(..., task=...) ; the checkpoint vocabulary comes from the training set, not the task.
  • See OneFormer docs and Loading Weights .
  • Community / upstream safetensors still work via the hf: prefix, e.g. OneFormerUniversalSegment.from_weights("hf:shi-labs/oneformer_cityscapes_swin_large") .
Special Thanks

A huge thank you to the SHI Labs OneFormer authors for creating and releasing these models.

License: MIT.

Runs of zeromodels oneformer_cityscapes_swin_large on huggingface.co

32
Total runs
-1
24-hour runs
-1
3-day runs
-10
7-day runs
-1
30-day runs

More Information About oneformer_cityscapes_swin_large huggingface.co Model

More oneformer_cityscapes_swin_large license Visit here:

https://choosealicense.com/licenses/mit

oneformer_cityscapes_swin_large huggingface.co

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

oneformer_cityscapes_swin_large huggingface.co Url

https://huggingface.co/zeromodels/oneformer_cityscapes_swin_large

zeromodels oneformer_cityscapes_swin_large online free

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

zeromodels oneformer_cityscapes_swin_large online free url in huggingface.co:

https://huggingface.co/zeromodels/oneformer_cityscapes_swin_large

oneformer_cityscapes_swin_large install

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

oneformer_cityscapes_swin_large install url in huggingface.co:

https://huggingface.co/zeromodels/oneformer_cityscapes_swin_large

Url of oneformer_cityscapes_swin_large

oneformer_cityscapes_swin_large huggingface.co Url

Provider of oneformer_cityscapes_swin_large huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels