| --- |
| pipeline_tag: image-segmentation |
| license: mit |
| base_model: facebook/mask2former-swin-tiny-coco-instance |
| library_name: zeromodels |
| tags: |
| - keras |
| - zeromodels |
| - mask2former |
| - instance-segmentation |
| - image-segmentation |
| - arxiv:2112.01527 |
| - pytorch |
| - jax |
| - tf |
| --- |
| |
| ## ***See [our collection](https://huggingface.co/collections/zeromodels/mask2former-6a8eaf66faaf81a53d54fa03) for all versions of Mask2Former.*** |
|
|
| # Run Mask2Former with Keras 3: JAX, PyTorch, or TensorFlow |
|
|
| [](https://github.com/IMvision12/ZeroModels) [](https://imvision12.github.io/ZeroModels/mask2former/) [](https://huggingface.co/collections/zeromodels/mask2former-6a8eaf66faaf81a53d54fa03) |
|
|
| # zeromodels/mask2former-swin-tiny-coco-instance |
|
|
| Paper: [Masked-attention Mask Transformer for Universal Image Segmentation (arXiv:2112.01527)](https://arxiv.org/abs/2112.01527) · [HF Papers](https://huggingface.co/papers/2112.01527) |
|
|
| 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](https://huggingface.co/facebook/mask2former-swin-tiny-coco-instance). |
|
|
| Pure-**Keras 3** conversion of [`facebook/mask2former-swin-tiny-coco-instance`](https://huggingface.co/facebook/mask2former-swin-tiny-coco-instance) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**. |
|
|
| This is a **instance** checkpoint (`Mask2FormerUniversalSegment`) (trained for instance; architecture is universal). |
|
|
| ## ✨ Quick start |
|
|
| ```python |
| import os |
| os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow" |
| |
| from PIL import Image |
| from zeromodels.models.mask2former import Mask2FormerUniversalSegment, Mask2FormerImageProcessor |
| |
| model = Mask2FormerUniversalSegment.from_weights("zeromodels/mask2former-swin-tiny-coco-instance") |
| processor = Mask2FormerImageProcessor.from_weights("zeromodels/mask2former-swin-tiny-coco-instance") |
| |
| 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 Mask2Former variant the same way with `from_weights("zeromodels/<variant>")`: |
|
|
| | Variant | Hub | Task | |
| |---|---|---| |
| | `mask2former-swin-tiny-coco-instance` | [`zeromodels/mask2former-swin-tiny-coco-instance`](https://huggingface.co/zeromodels/mask2former-swin-tiny-coco-instance) | instance | |
| | `mask2former-swin-small-coco-instance` | [`zeromodels/mask2former-swin-small-coco-instance`](https://huggingface.co/zeromodels/mask2former-swin-small-coco-instance) | instance | |
| | `mask2former-swin-base-coco-instance` | [`zeromodels/mask2former-swin-base-coco-instance`](https://huggingface.co/zeromodels/mask2former-swin-base-coco-instance) | instance | |
| | `mask2former-swin-large-coco-instance` | [`zeromodels/mask2former-swin-large-coco-instance`](https://huggingface.co/zeromodels/mask2former-swin-large-coco-instance) | instance | |
| | `mask2former-swin-tiny-coco-panoptic` | [`zeromodels/mask2former-swin-tiny-coco-panoptic`](https://huggingface.co/zeromodels/mask2former-swin-tiny-coco-panoptic) | panoptic | |
| | `mask2former-swin-tiny-ade-semantic` | [`zeromodels/mask2former-swin-tiny-ade-semantic`](https://huggingface.co/zeromodels/mask2former-swin-tiny-ade-semantic) | semantic | |
|
|
| ## Tips |
|
|
| - Set `KERAS_BACKEND` **before** importing Keras / zeromodels. |
| - The task suffix is what the checkpoint was trained for; post-process accordingly. |
| - See [Mask2Former docs]({DOCS_URL}) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/). |
| - Community / upstream weights: `Mask2FormerUniversalSegment.from_weights("hf:facebook/mask2former-swin-tiny-coco-instance")`. |
|
|
| ## Special Thanks |
|
|
| A huge thank you to the Facebook AI Research Mask2Former authors for creating and releasing these models. |
|
|
| License: MIT. |
|
|
