fix readme.md

README.md

@@ -1,21 +1,76 @@
 ---
 pipeline_tag: image-segmentation
 license: mit
+base_model: tue-mps/coco_instance_eomt_large_640
 library_name: kerasformers
 tags:
 - keras
 - kerasformers
 - eomt
-- tf
-- jax
+- instance-segmentation
+- image-segmentation
+- arxiv:2503.19108
 - pytorch
+- jax
+- tf
 ---
 
-# eomt_large_coco_instance_640 (Keras 3)
+## ***See [our collection](https://huggingface.co/collections/kerasformers/eomt-6a6a8e0309f2602fa0b94bb8) for all versions of EoMT.***
+
+# Run EoMT with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-EoMT-blue)](https://imvision12.github.io/KerasFormers/eomt/) [![Collection](https://img.shields.io/badge/HF-EoMT%20collection-yellow)](https://huggingface.co/collections/kerasformers/eomt-6a6a8e0309f2602fa0b94bb8)
+
+# kerasformers/eomt_large_coco_instance_640
+
+Paper: [Your ViT is Secretly an Image Segmentation Model (arXiv:2503.19108)](https://arxiv.org/abs/2503.19108) · [HF Papers](https://huggingface.co/papers/2503.19108)
+
+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.\n
+For more details on the model, please go to the upstream [model card](https://huggingface.co/tue-mps/coco_instance_eomt_large_640).
+
+Pure-**Keras 3** conversion of [`tue-mps/coco_instance_eomt_large_640`](https://huggingface.co/tue-mps/coco_instance_eomt_large_640) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is a **instance** checkpoint (`EoMTUniversalSegment`).
 
-Pure-Keras 3 weights for [kerasformers](https://github.com/IMvision12/KerasFormers), mirrored from the source. License: `mit`.
+## ✨ Quick start
 
 ```python
-from kerasformers.models.eomt import EoMTUniversalSegment
-model = EoMTUniversalSegment.from_weights("eomt_large_coco_instance_640")
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+from {meta['import_path']} import {meta['load_cls']}, {meta['proc_cls']}
+
+model = {meta["load_cls"]}.from_weights("kerasformers/{variant}")
+processor = {meta['proc_cls']}()
+
+image = Image.open("your_image.jpg").convert("RGB")
+output = model(processor(image)["pixel_values"], training=False)
+result = processor.post_process_instance_segmentation(
+    output, target_size=(image.height, image.width)
+)
+print(result.keys())
 ```
+
+Load any EoMT variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub | Task |
+|---|---|---|
+| `eomt_small_coco_panoptic_640` | [`kerasformers/eomt_small_coco_panoptic_640`](https://huggingface.co/kerasformers/eomt_small_coco_panoptic_640) | panoptic |
+| `eomt_base_coco_panoptic_640` | [`kerasformers/eomt_base_coco_panoptic_640`](https://huggingface.co/kerasformers/eomt_base_coco_panoptic_640) | panoptic |
+| `eomt_large_coco_panoptic_640` | [`kerasformers/eomt_large_coco_panoptic_640`](https://huggingface.co/kerasformers/eomt_large_coco_panoptic_640) | panoptic |
+| `eomt_large_coco_instance_640` | [`kerasformers/eomt_large_coco_instance_640`](https://huggingface.co/kerasformers/eomt_large_coco_instance_640) | instance |
+| `eomt_large_ade20k_semantic_512` | [`kerasformers/eomt_large_ade20k_semantic_512`](https://huggingface.co/kerasformers/eomt_large_ade20k_semantic_512) | semantic |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Use the post-processor that matches the checkpoint task (panoptic / instance / semantic).
+- See [EoMT docs]({DOCS_URL}) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- Community / upstream weights: `EoMTUniversalSegment.from_weights("hf:tue-mps/coco_instance_eomt_large_640")`.
+
+## Special Thanks
+
+A huge thank you to the TU/e MPS EoMT authors for creating and releasing these models.
+
+License: MIT.