Maskformer Swin Tiny Coco

🚀 MaskFormer

MaskFormer是一个在COCO全景分割数据集上训练的模型（微型版本，采用Swin骨干网络）。它解决了实例分割、语义分割和全景分割等任务，为图像分割领域带来了新的解决方案。

🚀 快速开始

你可以使用以下代码示例来使用这个模型进行语义分割：

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"]

更多代码示例，请参考文档。

✨ 主要特性

MaskFormer采用相同的范式来处理实例分割、语义分割和全景分割：通过预测一组掩码和相应的标签。因此，所有这3个任务都被视为实例分割任务。

📚 详细文档

预期用途和限制

你可以使用这个特定的检查点进行语义分割。查看模型中心，以寻找其他针对你感兴趣的任务进行微调的版本。

使用说明

这里展示了如何使用这个模型：

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

# 加载在COCO全景分割上微调的MaskFormer模型
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)
# 模型预测形状为 `(batch_size, num_queries)` 的 class_queries_logits
# 以及形状为 `(batch_size, num_queries, height, width)` 的 masks_queries_logits
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits

# 你可以将它们传递给特征提取器进行后处理
result = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# 我们参考演示笔记本进行可视化（请参阅MaskFormer文档中的“资源”部分）
predicted_panoptic_map = result["segmentation"]

📄 许可证

许可证类型：other