许可协议: MIT 标签:

• 视觉
• 图像分割 小部件:
• 示例图片: >- https://images.unsplash.com/photo-1643310325061-2beef64926a5?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8Nnx8cmFjb29uc3xlbnwwfHwwfHw%3D&w=1000&q=80 示例标题: 人物
• 示例图片: >- https://freerangestock.com/sample/139043/young-man-standing-and-leaning-on-car.jpg 示例标题: 人物 数据集:
• mattmdjaga/human_parsing_dataset 管道标签: 图像分割

用于服装分割的Segformer B3微调模型

基于ATR数据集微调的SegFormer模型，主要用于服装分割，但也可用于人体分割。在Hugging Face上的数据集名为"mattmdjaga/human_parsing_dataset"。

最新动态 - 训练代码。目前仅包含带有注释的纯代码，但很快将添加Colab笔记本版本和配套博客文章，使其更易使用。

from transformers import SegformerImageProcessor, AutoModelForSemanticSegmentation
from PIL import Image
import requests
import matplotlib.pyplot as plt
import torch.nn as nn

processor = SegformerImageProcessor.from_pretrained("sayeed99/segformer_b3_clothes")
model = AutoModelForSemanticSegmentation.from_pretrained("sayeed99/segformer_b3_clothes")

url = "https://plus.unsplash.com/premium_photo-1673210886161-bfcc40f54d1f?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8MXx8cGVyc29uJTIwc3RhbmRpbmd8ZW58MHx8MHx8&w=1000&q=80"

image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

outputs = model(**inputs)
logits = outputs.logits.cpu()

upsampled_logits = nn.functional.interpolate(
    logits,
    size=image.size[::-1],
    mode="bilinear",
    align_corners=False,
)

pred_seg = upsampled_logits.argmax(dim=1)[0]
plt.imshow(pred_seg)

标签: 0: "背景", 1: "帽子", 2: "头发", 3: "太阳镜", 4: "上衣", 5: "裙子", 6: "裤子", 7: "连衣裙", 8: "腰带", 9: "左鞋", 10: "右鞋", 11: "面部", 12: "左腿", 13: "右腿", 14: "左臂", 15: "右臂", 16: "包", 17: "围巾"

评估结果

整体评估指标:

• 评估损失: 0.15
• 平均准确率: 0.80
• 平均IoU: 0.69

许可协议

本模型的许可协议可在此处查看。

BibTeX引用信息

@article{DBLP:journals/corr/abs-2105-15203,
  author    = {Enze Xie and
               Wenhai Wang and
               Zhiding Yu and
               Anima Anandkumar and
               Jose M. Alvarez and
               Ping Luo},
  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
               Transformers},
  journal   = {CoRR},
  volume    = {abs/2105.15203},
  year      = {2021},
  url       = {https://arxiv.org/abs/2105.15203},
  eprinttype = {arXiv},
  eprint    = {2105.15203},
  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}