MaskFormer

MaskFormer模型在COCO panoptic segmentation上进行训练（tiny版本，采用Swin骨干网络）。该模型首次在 this repository 中发布，并在 Per-Pixel Classification is Not All You Need for Semantic Segmentation 中进行了介绍。

免责声明：发布MaskFormer模型的团队并未为此模型编写模型卡片，因此该模型卡片由Hugging Face团队编写。

模型描述

MaskFormer通过预测一组掩码和相应的标签，处理实例分割、语义分割和全景分割这三个任务。因此，这三个任务都被视为实例分割。

预期用途和限制

您可以使用此特定的检查点来进行语义分割。查看 model hub 以寻找您感兴趣的其他任务的精调版本。

如何使用

以下是如何使用此模型的方法：

from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
from PIL import Image
import requests

# load MaskFormer fine-tuned on COCO panoptic segmentation
feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-tiny-coco")
model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-tiny-coco")

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

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 feature_extractor for postprocessing
result = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_panoptic_map = result["segmentation"]

有关更多代码示例，请参阅 documentation 。