Maskformer Swin Tiny Ade

🚀 MaskFormer

MaskFormer是一个在ADE20k语义分割数据集上训练的模型（微小版本，采用Swin骨干网络）。它在论文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。该模型使用相同的范式处理实例、语义和全景分割任务，通过预测一组掩码和相应的标签，将这3种任务都视为实例分割任务。

🚀 快速开始

本模型适用于语义分割任务。你可以在模型中心查找其他针对你感兴趣任务的微调版本。

以下是使用该模型的示例代码：

from transformers import MaskFormerFeatureExtractor, 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)
feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-tiny-ade")
inputs = feature_extractor(images=image, return_tensors="pt")

model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-tiny-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 feature_extractor for postprocessing
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_semantic_map = feature_extractor.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使用相同的范式处理实例、语义和全景分割任务，即通过预测一组掩码和相应的标签，将所有这3种任务都视为实例分割任务。

📄 许可证

许可证类型：other

📦 相关信息

⚠️ 重要提示

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。