Oneformer Coco Swin Large

🚀 OneFormer

OneFormer is a model trained on the COCO dataset (large-sized version, Swin backbone). It offers a unified solution for universal image segmentation.

🚀 Quick Start

OneFormer is a remarkable model for image segmentation. It was introduced in the paper OneFormer: One Transformer to Rule Universal Image Segmentation by Jain et al. and first released in this repository.

✨ Features

OneFormer is the first multi - task universal image segmentation framework. With a single universal architecture, a single model, and training on a single dataset, it can outperform existing specialized models in semantic, instance, and panoptic segmentation tasks. It uses a task token to guide the model during training and make it dynamic during inference, all with just one model.

📚 Documentation

Intended uses & limitations

You can use this particular checkpoint for semantic, instance, and panoptic segmentation. Check the model hub to find other fine - tuned versions on different datasets.

How to use

💻 Usage Examples

Basic Usage

from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
from PIL import Image
import requests
url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/coco.jpeg"
image = Image.open(requests.get(url, stream=True).raw)

# Loading a single model for all three tasks
processor = OneFormerProcessor.from_pretrained("shi-labs/oneformer_coco_swin_large")
model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_coco_swin_large")

# Semantic Segmentation
semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt")
semantic_outputs = model(**semantic_inputs)
# pass through image_processor for postprocessing
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]

# Instance Segmentation
instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt")
instance_outputs = model(**instance_inputs)
# pass through image_processor for postprocessing
predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]

# Panoptic Segmentation
panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt")
panoptic_outputs = model(**panoptic_inputs)
# pass through image_processor for postprocessing
predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]

For more examples, please refer to the documentation.

Citation

@article{jain2022oneformer,
      title={{OneFormer: One Transformer to Rule Universal Image Segmentation}},
      author={Jitesh Jain and Jiachen Li and MangTik Chiu and Ali Hassani and Nikita Orlov and Humphrey Shi},
      journal={arXiv}, 
      year={2022}
    }

📄 License

This project is licensed under the MIT license.