zeromodels / eomt_base_coco_panoptic_640

huggingface.co
Total runs: 131
24-hour runs: 2
7-day runs: 5
30-day runs: -3
Model's Last Updated: August 27 2026
image-segmentation

Introduction of eomt_base_coco_panoptic_640

Model Details of eomt_base_coco_panoptic_640

See our collection for all versions of EoMT.

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

GitHub Docs Collection

zeromodels/eomt_base_coco_panoptic_640

Paper: Your ViT is Secretly an Image Segmentation Model (arXiv:2503.19108) · HF Papers

EoMT (Encoder-only Mask Transformer) keeps segmentation inside a plain ViT: learned query tokens are concatenated with patch tokens and run through the same ViT blocks. No pixel decoder, no deformable attention decoder.

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

Pure- Keras 3 conversion of tue-mps/coco_panoptic_eomt_base_640_2x for zeromodels . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a panoptic checkpoint ( EoMTUniversalSegment ).

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

from PIL import Image
from zeromodels.models.eomt import EoMTUniversalSegment, EoMTImageProcessor

model = EoMTUniversalSegment.from_weights("zeromodels/eomt_base_coco_panoptic_640")
processor = EoMTImageProcessor.from_weights("zeromodels/eomt_base_coco_panoptic_640")

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

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

Variant Hub Task
eomt_small_coco_panoptic_640 zeromodels/eomt_small_coco_panoptic_640 panoptic
eomt_base_coco_panoptic_640 zeromodels/eomt_base_coco_panoptic_640 panoptic
eomt_large_coco_panoptic_640 zeromodels/eomt_large_coco_panoptic_640 panoptic
eomt_large_coco_instance_640 zeromodels/eomt_large_coco_instance_640 instance
eomt_large_ade20k_semantic_512 zeromodels/eomt_large_ade20k_semantic_512 semantic
Tips
  • Set KERAS_BACKEND before importing Keras / zeromodels.
  • Use the post-processor that matches the checkpoint task (panoptic / instance / semantic).
  • See EoMT docs and Loading Weights .
  • Community / upstream weights: EoMTUniversalSegment.from_weights("hf:tue-mps/coco_panoptic_eomt_base_640_2x") .
Special Thanks

A huge thank you to the TU/e MPS EoMT authors for creating and releasing these models.

License: MIT.

Runs of zeromodels eomt_base_coco_panoptic_640 on huggingface.co

131
Total runs
2
24-hour runs
3
3-day runs
5
7-day runs
-3
30-day runs

More Information About eomt_base_coco_panoptic_640 huggingface.co Model

More eomt_base_coco_panoptic_640 license Visit here:

https://choosealicense.com/licenses/mit

eomt_base_coco_panoptic_640 huggingface.co

eomt_base_coco_panoptic_640 huggingface.co is an AI model on huggingface.co that provides eomt_base_coco_panoptic_640's model effect (), which can be used instantly with this zeromodels eomt_base_coco_panoptic_640 model. huggingface.co supports a free trial of the eomt_base_coco_panoptic_640 model, and also provides paid use of the eomt_base_coco_panoptic_640. Support call eomt_base_coco_panoptic_640 model through api, including Node.js, Python, http.

eomt_base_coco_panoptic_640 huggingface.co Url

https://huggingface.co/zeromodels/eomt_base_coco_panoptic_640

zeromodels eomt_base_coco_panoptic_640 online free

eomt_base_coco_panoptic_640 huggingface.co is an online trial and call api platform, which integrates eomt_base_coco_panoptic_640's modeling effects, including api services, and provides a free online trial of eomt_base_coco_panoptic_640, you can try eomt_base_coco_panoptic_640 online for free by clicking the link below.

zeromodels eomt_base_coco_panoptic_640 online free url in huggingface.co:

https://huggingface.co/zeromodels/eomt_base_coco_panoptic_640

eomt_base_coco_panoptic_640 install

eomt_base_coco_panoptic_640 is an open source model from GitHub that offers a free installation service, and any user can find eomt_base_coco_panoptic_640 on GitHub to install. At the same time, huggingface.co provides the effect of eomt_base_coco_panoptic_640 install, users can directly use eomt_base_coco_panoptic_640 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

eomt_base_coco_panoptic_640 install url in huggingface.co:

https://huggingface.co/zeromodels/eomt_base_coco_panoptic_640

Url of eomt_base_coco_panoptic_640

eomt_base_coco_panoptic_640 huggingface.co Url

Provider of eomt_base_coco_panoptic_640 huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels