zeromodels / mask2former-swin-tiny-ade-semantic

huggingface.co
Total runs: 36
24-hour runs: 2
7-day runs: -7
30-day runs: -3
Model's Last Updated: August 27 2026
image-segmentation

Introduction of mask2former-swin-tiny-ade-semantic

Model Details of mask2former-swin-tiny-ade-semantic

See our collection for all versions of Mask2Former.

Run Mask2Former with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Docs Collection

kerasformers/mask2former-swin-tiny-ade-semantic

Paper: Masked-attention Mask Transformer for Universal Image Segmentation (arXiv:2112.01527) · HF Papers

Mask2Former improves MaskFormer with masked attention in the transformer decoder, restricting cross-attention to predicted mask regions for sharper boundaries and stronger universal segmentation.

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

Pure- Keras 3 conversion of facebook/mask2former-swin-tiny-ade-semantic for kerasformers . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a semantic checkpoint ( Mask2FormerUniversalSegment ) (trained for semantic; architecture is universal).

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

from PIL import Image
from kerasformers.models.mask2former import Mask2FormerUniversalSegment, Mask2FormerImageProcessor

model = Mask2FormerUniversalSegment.from_weights("kerasformers/mask2former-swin-tiny-ade-semantic")
processor = Mask2FormerImageProcessor.from_weights("kerasformers/mask2former-swin-tiny-ade-semantic")

image = Image.open("your_image.jpg").convert("RGB")
output = model(processor(image)["pixel_values"], training=False)
result = processor.post_process_semantic_segmentation(
    output, target_size=(image.height, image.width)
)
print(result["segmentation"].shape)

Load any Mask2Former variant the same way with from_weights("kerasformers/<variant>") :

Variant Hub Task
mask2former-swin-tiny-coco-instance kerasformers/mask2former-swin-tiny-coco-instance instance
mask2former-swin-small-coco-instance kerasformers/mask2former-swin-small-coco-instance instance
mask2former-swin-base-coco-instance kerasformers/mask2former-swin-base-coco-instance instance
mask2former-swin-large-coco-instance kerasformers/mask2former-swin-large-coco-instance instance
mask2former-swin-tiny-coco-panoptic kerasformers/mask2former-swin-tiny-coco-panoptic panoptic
mask2former-swin-tiny-ade-semantic kerasformers/mask2former-swin-tiny-ade-semantic semantic
Tips
  • Set KERAS_BACKEND before importing Keras / kerasformers.
  • The task suffix is what the checkpoint was trained for; post-process accordingly.
  • See Mask2Former docs and Loading Weights .
  • Community / upstream weights: Mask2FormerUniversalSegment.from_weights("hf:facebook/mask2former-swin-tiny-ade-semantic") .
Special Thanks

A huge thank you to the Facebook AI Research Mask2Former authors for creating and releasing these models.

License: MIT.

Runs of zeromodels mask2former-swin-tiny-ade-semantic on huggingface.co

36
Total runs
2
24-hour runs
-3
3-day runs
-7
7-day runs
-3
30-day runs

More Information About mask2former-swin-tiny-ade-semantic huggingface.co Model

More mask2former-swin-tiny-ade-semantic license Visit here:

https://choosealicense.com/licenses/mit

mask2former-swin-tiny-ade-semantic huggingface.co

mask2former-swin-tiny-ade-semantic huggingface.co is an AI model on huggingface.co that provides mask2former-swin-tiny-ade-semantic's model effect (), which can be used instantly with this zeromodels mask2former-swin-tiny-ade-semantic model. huggingface.co supports a free trial of the mask2former-swin-tiny-ade-semantic model, and also provides paid use of the mask2former-swin-tiny-ade-semantic. Support call mask2former-swin-tiny-ade-semantic model through api, including Node.js, Python, http.

mask2former-swin-tiny-ade-semantic huggingface.co Url

https://huggingface.co/zeromodels/mask2former-swin-tiny-ade-semantic

zeromodels mask2former-swin-tiny-ade-semantic online free

mask2former-swin-tiny-ade-semantic huggingface.co is an online trial and call api platform, which integrates mask2former-swin-tiny-ade-semantic's modeling effects, including api services, and provides a free online trial of mask2former-swin-tiny-ade-semantic, you can try mask2former-swin-tiny-ade-semantic online for free by clicking the link below.

zeromodels mask2former-swin-tiny-ade-semantic online free url in huggingface.co:

https://huggingface.co/zeromodels/mask2former-swin-tiny-ade-semantic

mask2former-swin-tiny-ade-semantic install

mask2former-swin-tiny-ade-semantic is an open source model from GitHub that offers a free installation service, and any user can find mask2former-swin-tiny-ade-semantic on GitHub to install. At the same time, huggingface.co provides the effect of mask2former-swin-tiny-ade-semantic install, users can directly use mask2former-swin-tiny-ade-semantic installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mask2former-swin-tiny-ade-semantic install url in huggingface.co:

https://huggingface.co/zeromodels/mask2former-swin-tiny-ade-semantic

Url of mask2former-swin-tiny-ade-semantic

mask2former-swin-tiny-ade-semantic huggingface.co Url

Provider of mask2former-swin-tiny-ade-semantic huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels