Segformer B3 Fashion

🚀 segformer-b3-fashion

segformer-b3-fashion 是一个图像分割模型，它基于特定数据集进行微调，可对时尚相关的图像进行分割，识别多种时尚物品和服饰细节，在时尚图像分析等领域有重要应用价值。

🚀 快速开始

segformer-b3-fashion 模型是 nvidia/mit-b3 在 sayeed99/fashion_segmentation 数据集上的微调版本，微调过程使用原始图像尺寸，未进行缩放。

以下是使用该模型进行图像分割的示例代码：

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("sayeed99/segformer-b3-fashion")
model = AutoModelForSemanticSegmentation.from_pretrained("sayeed99/segformer-b3-fashion")

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)

💻 使用示例

基础用法

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-fashion")
model = AutoModelForSemanticSegmentation.from_pretrained("sayeed99/segformer-b3-fashion")

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)

标签说明

模型的分割标签如下： {"0":"未标记", "1": "衬衫、短上衣", "2": "上衣、T恤、运动衫", "3": "毛衣", "4": "开襟羊毛衫", "5": "夹克", "6": "背心", "7": "裤子", "8": "短裤", "9": "裙子", "10": "外套", "11": "连衣裙", "12": "连身裤", "13": "披肩", "14": "眼镜", "15": "帽子", "16": "头带、头巾、发饰", "17": "领带", "18": "手套", "19": "手表", "20": "腰带", "21": "腿套", "22": "紧身裤、长袜", "23": "袜子", "24": "鞋子", "25": "包、钱包", "26": "围巾", "27": "雨伞", "28": "兜帽", "29": "衣领", "30": "翻领", "31": "肩章", "32": "袖子", "33": "口袋", "34": "领口", "35": "搭扣", "36": "拉链", "37": "贴花", "38": "珠子", "39": "蝴蝶结", "40": "花朵", "41": "流苏", "42": "丝带", "43": "铆钉", "44": "褶边", "45": "亮片", "46": "缨穗"}

📚 详细文档

框架版本

• Transformers 4.30.0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3

📄 许可证

该模型的许可证信息可在 此处 查看。

📖 引用格式

@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}
}