license: mit tags:

• vision
• image-segmentation widget:
• src: https://images.unsplash.com/photo-1643310325061-2beef64926a5?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8Nnx8cmFjb29uc3xlbnwwfHwwfHw%3D&w=1000&q=80 example_title: Person
• src: https://freerangestock.com/sample/139043/young-man-standing-and-leaning-on-car.jpg example_title: Person datasets:
• mattmdjaga/human_parsing_dataset

Segformer B2 服装分割微调模型

SegFormer 模型在 ATR 数据集 上微调用于服装分割，但也可用于人体分割。 Hugging Face 上的数据集名称为 "mattmdjaga/human_parsing_dataset"。

训练代码。

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("mattmdjaga/segformer_b2_clothes")
model = AutoModelForSemanticSegmentation.from_pretrained("mattmdjaga/segformer_b2_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: "Background"（背景）, 1: "Hat"（帽子）, 2: "Hair"（头发）, 3: "Sunglasses"（太阳镜）, 4: "Upper-clothes"（上装）, 5: "Skirt"（裙子）, 6: "Pants"（裤子）, 7: "Dress"（连衣裙）, 8: "Belt"（腰带）, 9: "Left-shoe"（左鞋）, 10: "Right-shoe"（右鞋）, 11: "Face"（脸部）, 12: "Left-leg"（左腿）, 13: "Right-leg"（右腿）, 14: "Left-arm"（左臂）, 15: "Right-arm"（右臂）, 16: "Bag"（包）, 17: "Scarf"（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

许可证

本模型的许可证可在此处找到。

BibTeX 条目和引用信息

@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}
}