模型:

facebook/mask2former-swin-base-coco-instance

英文

Mask2Former

Mask2Former模型在COCO实例分割上进行了训练(基于尺寸的版本,使用Swin骨干)。该模型在 Masked-attention Mask Transformer for Universal Image Segmentation 论文中首次提出,并于 this repository 首次发布。

免责声明:发布Mask2Former的团队没有为该模型编写模型卡片,所以此模型卡片由Hugging Face团队编写。

模型描述

Mask2Former通过预测一组掩码和相应的标签来解决实例分割、语义分割和全景分割的问题。因此,这三个任务都被视为实例分割。Mask2Former通过以下方式在性能和效率上优于之前的SOTA模型 MaskFormer :(i) 用更先进的多尺度可变形注意力Transformer替代像素解码器,(ii) 采用具有掩码注意力的Transformer解码器,在不引入额外计算的同时提高性能,(iii) 通过在子采样点上计算损失而不是整个掩码来提高训练效率。

预期用途和限制

您可以使用此特定检查点进行实例分割。请参阅 model hub 以查找您感兴趣的任务的其他微调版本。

使用方法

下面是如何使用此模型的方法:

import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation


# load Mask2Former fine-tuned on COCO instance segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-base-coco-instance")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-base-coco-instance")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    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
result = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
predicted_instance_map = result["segmentation"]

有关更多代码示例,请参考 documentation