Oneformer Cityscapes Swin Large

🚀 OneFormer

OneFormer是在Cityscapes数据集（大尺寸版本，Swin主干网络）上训练的模型。它由Jain等人在论文 OneFormer: One Transformer to Rule Universal Image Segmentation 中提出，并首次在 此仓库 中发布。该模型可用于解决图像分割相关问题，为图像分割任务提供了统一的解决方案。

🚀 快速开始

模型描述

OneFormer是首个多任务通用图像分割框架。它仅需使用单一通用架构、单个模型，并在单个数据集上进行一次训练，就能在语义分割、实例分割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聚焦于当前任务，使得该架构在训练时以任务为导向，在推理时具有任务动态性，且仅需单个模型即可实现。

预期用途和限制

你可以使用此特定检查点进行语义分割、实例分割和全景分割。请查看 模型中心 以查找在不同数据集上微调的其他版本。

如何使用

以下是如何使用此模型的示例：

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/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"]

更多示例请参考 文档。

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