SegFormer_b2_clothes Open-Source Model - Achieve Precise Clothing and Human Body Segmentation for Free

Home

Segformer B2 Clothes

Developed by mattmdjaga

SegFormer model fine-tuned on ATR dataset for clothing and human segmentation

Image Segmentation

Transformers

Open Source License:MIT #Clothing Segmentation #Human Part Recognition #Multi-class Segmentation

Downloads 666.39k

Release Time : 11/24/2022

Model Overview

This is a vision segmentation model based on the SegFormer architecture, specifically designed for clothing and human segmentation tasks. The model can identify and segment 18 different clothing and body part categories in images.

Model Features

Fine-grained Clothing Segmentation

Capable of identifying and segmenting 18 different clothing and body part categories, including tops, pants, shoes, etc.

SegFormer Architecture

Utilizes the efficient SegFormer Transformer architecture, combining the advantages of Transformers with the requirements of semantic segmentation tasks

High-precision Segmentation

Achieves high accuracy across multiple categories, particularly with over 90% recognition accuracy for hair, face, and major clothing categories

Model Capabilities

Image Segmentation

Clothing Recognition

Human Part Recognition

Visual Scene Understanding

Use Cases

Fashion & Retail

Virtual Try-on

Supports virtual try-on applications through accurate clothing segmentation

Fashion Recommendation

Analyzes user's dressing style to provide personalized fashion suggestions

Human-Computer Interaction

Augmented Reality Applications

Enables precise human part and clothing recognition in AR applications

🚀 Segformer B2 fine-tuned for clothes segmentation

A fine-tuned SegFormer model for clothes and human segmentation, trained on the ATR dataset.

🚀 Quick Start

The SegFormer model is fine-tuned on the ATR dataset for clothes segmentation and can also be used for human segmentation. The dataset on Hugging Face is named "mattmdjaga/human_parsing_dataset".

Training code.

💻 Usage Examples

Basic Usage

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)

Labels

Labels: 0: "Background", 1: "Hat", 2: "Hair", 3: "Sunglasses", 4: "Upper-clothes", 5: "Skirt", 6: "Pants", 7: "Dress", 8: "Belt", 9: "Left-shoe", 10: "Right-shoe", 11: "Face", 12: "Left-leg", 13: "Right-leg", 14: "Left-arm", 15: "Right-arm", 16: "Bag", 17: "Scarf"

📚 Documentation

Evaluation

Label Index	Label Name	Category Accuracy	Category IoU
0	Background	0.99	0.99
1	Hat	0.73	0.68
2	Hair	0.91	0.82
3	Sunglasses	0.73	0.63
4	Upper-clothes	0.87	0.78
5	Skirt	0.76	0.65
6	Pants	0.90	0.84
7	Dress	0.74	0.55
8	Belt	0.35	0.30
9	Left-shoe	0.74	0.58
10	Right-shoe	0.75	0.60
11	Face	0.92	0.85
12	Left-leg	0.90	0.82
13	Right-leg	0.90	0.81
14	Left-arm	0.86	0.74
15	Right-arm	0.82	0.73
16	Bag	0.91	0.84
17	Scarf	0.63	0.29

Overall Evaluation Metrics:

Evaluation Loss: 0.15
Mean Accuracy: 0.80
Mean IoU: 0.69

📄 License

The license for this model can be found here.

📚 BibTeX entry and citation info

@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}
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご