Maskformer Swin Large Ade

🚀 MaskFormer

MaskFormer是一個在ADE20k語義分割數據集上訓練的模型（大型版本，採用Swin骨幹網絡）。該模型解決了實例、語義和全景分割問題，為圖像分割領域提供了高效的解決方案。

🚀 快速開始

你可以使用此特定檢查點進行語義分割。若想尋找針對其他感興趣任務的微調版本，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]

更多代碼示例請參考文檔。

✨ 主要特性

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

💻 使用示例

基礎用法

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]

高級用法

如需更多高級使用場景，請參考文檔中的代碼示例。

📚 詳細文檔

MaskFormer模型在論文 Per-Pixel Classification is Not All You Need for Semantic Segmentation 中被提出，並首次在 此倉庫 中發佈。

需注意，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。

📄 許可證

許可證類型：other