Oneformer Coco Swin Large

🚀 OneFormer

OneFormer是一个在COCO数据集上训练的模型（大尺寸版本，采用Swin骨干网络）。它能够有效解决图像分割问题，为语义、实例和全景分割任务提供了统一的解决方案，提升了图像分割的效率和准确性。

🚀 快速开始

OneFormer模型可用于语义、实例和全景分割任务。你可以参考以下使用示例对该模型进行调用。若需查找在其他数据集上微调的版本，请访问模型中心。

✨ 主要特性

• OneFormer是首个多任务通用图像分割框架。仅需使用单一通用架构、单一模型，并在单一数据集上进行一次训练，就能在语义、实例和全景分割任务中超越现有的专门模型。
• OneFormer使用任务令牌来使模型专注于当前任务，使架构在训练时具有任务导向性，在推理时具有任务动态性，且所有操作都基于单一模型完成。

💻 使用示例

基础用法

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"]

更多示例请参考文档。

📚 详细文档

预期用途和限制

你可以使用此特定检查点进行语义、实例和全景分割。若需查找在其他数据集上微调的版本，请访问模型中心。

引用

@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}
    }

📄 许可证

本项目采用MIT许可证。

信息表格

模型示例展示

交互小部件示例

• Person
• Airplane
• Corgi