Oneformer Cityscapes Swin Large

🚀 OneFormer

OneFormer是在Cityscapes數據集（大尺寸版本，Swin主幹網絡）上訓練的模型。它由Jain等人在論文 OneFormer: One Transformer to Rule Universal Image Segmentation 中提出，並首次在 此倉庫 中發佈。該模型可用於解決圖像分割相關問題，為圖像分割任務提供了統一的解決方案。

🚀 快速開始

模型描述

OneFormer是首個多任務通用圖像分割框架。它僅需使用單一通用架構、單個模型，並在單個數據集上進行一次訓練，就能在語義分割、實例分割和全景分割任務中超越現有的專門模型。OneFormer使用任務令牌來使模型聚焦於當前任務，使得該架構在訓練時以任務為導向，在推理時具有任務動態性，且僅需單個模型即可實現。

預期用途和限制

你可以使用此特定檢查點進行語義分割、實例分割和全景分割。請查看 模型中心 以查找在不同數據集上微調的其他版本。

如何使用

以下是如何使用此模型的示例：

基礎用法

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"]

更多示例請參考 文檔。

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}
    }

📄 許可證

本項目採用MIT許可證。

📋 信息表格