Maskformer Swin Base Coco

🚀 MaskFormer

MaskFormer 是一個用於圖像分割的模型，它基於相同的範式處理實例、語義和全景分割任務，通過預測一組掩碼和相應的標籤來實現，為圖像分割領域提供了高效的解決方案。

🚀 快速開始

模型描述

MaskFormer 以相同的範式處理實例、語義和全景分割：通過預測一組掩碼和相應的標籤。因此，所有這 3 個任務都被視為實例分割。

預期用途和限制

你可以使用此特定檢查點進行語義分割。請查看 模型中心 以查找針對你感興趣的任務進行微調的其他版本。

如何使用

基礎用法

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-base-coco")
model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-base-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"]

更多代碼示例，請參考 文檔。

📄 許可證

許可證類型：其他

📋 信息表格

免責聲明

發佈 MaskFormer 的團隊並未為此模型編寫模型卡片，此模型卡片由 Hugging Face 團隊編寫。該模型在論文 Per-Pixel Classification is Not All You Need for Semantic Segmentation 中被引入，並首次在 此倉庫 中發佈。