Mask2Former

Mask2Former模型是在ADE20k语义分割（大尺寸版本，Swin骨干）上训练的。该模型在论文 Masked-attention Mask Transformer for Universal Image Segmentation 中引入，于 this repository 首次发布。

免责声明：发布Mask2Former的团队没有为该模型撰写模型卡片，因此此模型卡片是由Hugging Face团队撰写的。

模型描述

Mask2Former通过预测一组掩码和相应的标签来解决实例、语义和全景分割。因此，所有三个任务都被视为实例分割。Mask2Former通过以下方式在性能和效率上优于先前的SOTA模型 MaskFormer ：（i）用更先进的多尺度可变形注意力Transformer替换像素解码器，（ii）采用具有蒙版注意力的Transformer解码器，以提高性能而不引入额外的计算，（iii）通过对子采样点计算损失而不是整个掩码来提高训练效率。

预期用途与限制

您可以将此特定检查点用于全景分割。查看 model hub 以寻找您感兴趣的其他任务的微调版本。

如何使用

以下是如何使用此模型：

import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation


# load Mask2Former fine-tuned on ADE20k semantic segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-ade-semantic")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-ade-semantic")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

# model predicts class_queries_logits of shape `(batch_size, num_queries)`
# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits

# you can pass them to processor for postprocessing
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)

有关更多代码示例，请参阅 documentation 。