Mask2former Swin Tiny Coco Panoptic

## 🚀 Mask2Former

*Mask2Former is a model trained on COCO panoptic segmentation (tiny-sized version, Swin backbone). It offers a unified approach for instance, semantic, and panoptic segmentation.*

## 🚀 Quick Start
Mask2Former is a powerful model for image segmentation tasks. It can handle instance, semantic, and panoptic segmentation using a single paradigm. You can use the provided code examples to quickly start with this model.

## ✨ Features
- **Unified Segmentation Paradigm**: Addresses instance, semantic, and panoptic segmentation with the same approach.
- **High Performance**: Outperforms the previous SOTA, MaskFormer, in terms of both performance and efficiency.
- **Advanced Architecture**: Utilizes a multi - scale deformable attention Transformer and a masked attention Transformer decoder.

## 📚 Documentation
### Model description
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, 
[MaskFormer](https://arxiv.org/abs/2107.06278) both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi - scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without
without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/mask2former_architecture.png)

### Intended uses & limitations
You can use this particular checkpoint for panoptic segmentation. See the [model hub](https://huggingface.co/models?search=mask2former) to look for other
fine - tuned versions on a task that interests you.

## 💻 Usage Examples
### Basic Usage
```python
import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation


# load Mask2Former fine-tuned on COCO panoptic segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-tiny-coco-panoptic")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-tiny-coco-panoptic")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

# model predicts class_queries_logits of shape `(batch_size, num_queries)`
# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits

# you can pass them to processor for postprocessing
result = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
predicted_panoptic_map = result["segmentation"]

Advanced Usage

For more code examples, we refer to the documentation.

📄 License

License: other

Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team.