Oneformer Cityscapes Swin Large

🚀 OneFormer

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

🚀 Quick Start

OneFormer is a remarkable model for image segmentation. You can utilize it for semantic, instance, and panoptic segmentation tasks.

✨ Features

• Multi - task Universal Segmentation: OneFormer is the first multi - task universal image segmentation framework. With a single universal architecture, model, and dataset training, it outperforms existing specialized models in semantic, instance, and panoptic segmentation tasks.
• Task - Guided and Task - Dynamic: It uses a task token to condition the model on the task in focus, enabling task - guided training and task - dynamic inference with a single model.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 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/cityscapes.png"
image = Image.open(requests.get(url, stream=True).raw)

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

📚 Documentation

Model description

OneFormer is the first multi - task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task - guided for training, and task - dynamic for inference, all with a single model.

Intended uses & limitations

You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the model hub to look for other fine - tuned versions on a different dataset.

🔧 Technical Details

No specific technical details beyond the model description are provided in the original document, so this section is skipped.

📄 License

This project is licensed under the MIT license.

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}
    }