Mask2Former模型是在COCO实例分割(小尺寸版本,Swin骨干网络)上训练的。该模型在论文 Masked-attention Mask Transformer for Universal Image Segmentation 中被介绍,并于 this repository 首次发布。
声明:发布Mask2Former模型的团队未为该模型编写模型卡片,因此本模型卡片由Hugging Face团队编写。
Mask2Former模型统一处理实例分割、语义分割和全景分割任务,采用相同的范式:预测一组掩码和相应的标签。因此,这3个任务都被视为实例分割。Mask2Former模型通过以下方式在性能和效率上优于之前的最优模型 MaskFormer :(i) 使用更先进的多尺度可变形注意力Transformer替换像素解码器,(ii) 采用具有掩码注意力的Transformer解码器以提高性能而不引入额外的计算量,(iii) 改进训练效率,通过在子采样点上计算损失而不是整个掩码。
您可以使用此特定检查点进行实例分割。查看 model hub 以寻找您感兴趣的其他任务的微调版本。
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-small-coco-instance") model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-small-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,请参阅 documentation 。