OneFormer

OneFormer模型是在ADE20k数据集上训练的（tiny-sized版本，Swin骨干）。该模型在Jain等人的论文 OneFormer: One Transformer to Rule Universal Image Segmentation 中首次提出，并在 this repository 中首次发布。

模型描述

OneFormer是第一个多任务通用图像分割框架。它只需要使用单个通用架构、单个模型和单个数据集进行训练，就能在语义、实例和全景分割任务上胜过现有的专用模型。OneFormer使用任务标记来使模型针对特定任务进行训练，从而使架构在训练过程中具有任务引导的特性，在推理过程中能够根据任务的变化而动态调整，而这一切都只需要一个模型。

预期用途和限制

您可以使用该特定检查点进行语义、实例和全景分割。请参阅 model hub 以查找在不同数据集上进行微调的其他版本。

如何使用

这是如何使用该模型的方法：

from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
from PIL import Image
import requests
url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.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_ade20k_swin_tiny")
model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_swin_tiny")

# 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，请参阅 documentation 。

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}
    }