Maskformer Swin Large Ade

🚀 MaskFormer

MaskFormer是一个在ADE20k语义分割数据集上训练的模型（大型版本，采用Swin骨干网络）。该模型解决了实例、语义和全景分割问题，为图像分割领域提供了高效的解决方案。

🚀 快速开始

你可以使用此特定检查点进行语义分割。若想寻找针对其他感兴趣任务的微调版本，可查看模型中心。

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

url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg"
image = Image.open(requests.get(url, stream=True).raw)

processor = MaskFormerImageProcessor.from_pretrained("facebook/maskformer-swin-large-ade")
inputs = processor(images=image, return_tensors="pt")

model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-ade")
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
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]

更多代码示例请参考文档。

✨ 主要特性

MaskFormer通过预测一组掩码和相应的标签，以相同的范式处理实例、语义和全景分割问题。因此，所有这3个任务都被视为实例分割任务。

💻 使用示例

基础用法

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

url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg"
image = Image.open(requests.get(url, stream=True).raw)

processor = MaskFormerImageProcessor.from_pretrained("facebook/maskformer-swin-large-ade")
inputs = processor(images=image, return_tensors="pt")

model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-ade")
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
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]

高级用法

如需更多高级使用场景，请参考文档中的代码示例。

📚 详细文档

MaskFormer模型在论文 Per-Pixel Classification is Not All You Need for Semantic Segmentation 中被提出，并首次在 此仓库 中发布。

需注意，发布MaskFormer的团队并未为此模型编写模型卡片，此模型卡片由Hugging Face团队编写。

📄 许可证

许可证类型：other