---
title: SegFormer ONNX
emoji: 🏃
colorFrom: indigo
colorTo: gray
sdk: gradio
sdk_version: 5.49.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: SegFormer image segmentation ADE20k, Cloths & Fashion
---

# [SegFormer image segmentation ADE20k, Cloths & Fashion](https://huggingface.co/spaces/leonelhs/segformer-tf-transformers )

This is demo collects SegFormer implementations from several spaces  

## Model ADE20k 
This model is fine-tuned for images belonging to scene categories.

## Model Cloths 
This model is fine-tuned for human cloth images.
Expected classes: Face, Hat, Hair, Upper_clothes, Skirt, Pants, Dress, Belt, shoe, leg, arm, Bag, Scarf

## Model Fashion 
This model extends and complements human cloth model.
Expected classes: shirt, top, sweater, cardigan, jacket, vest, pants, shorts, skirt, coat, dress, jumpsuit, cape, glasses, hat, hairaccessory, tie, glove, watch, belt, legwarmer, tights, sock, shoe, bagwallet, scarf, umbrella, hood, collar, lapel, epaulette, sleeve, pocket, neckline, buckle, zipper, applique, bead, bow, flower, fringe, ribbon, rivet, ruffle, sequin, tassel

## Acknowledgments
This work integrates code and concepts from several repositories.  
For proper attribution, please refer to the following sources (or notify us if any are missing):
- [github](https://github.com/deep-diver/segformer-tf-transformers)
- [huggingface](https://huggingface.co/spaces/chansung/segformer-tf-transformers)
- [ADE20k dataset](http://groups.csail.mit.edu/vision/datasets/ADE20K/)
- [nvidia](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640)
## Contact
For questions, comments, or feedback, please contact:  
📧 **leonelhs@gmail.com**