Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · sayeed99

segformer-b3-fashion

segformer-b3-fashion is a 47.26M-parameter Segformer image-segmentation fine-tune from sayeed99. According to the model card, it is a fine-tuned version of nvidia/mit-b3 on fashion_segmentation without resizing.

Publisher
sayeed99
Task
image-segmentation
Model type
segformer
License
other
Library
transformers
Publication status
Accepted · not indexed

Model overview

segformer-b3-fashion is published by sayeed99 as an image-segmentation model. The captured configuration identifies SegformerForSemanticSegmentation with model type segformer, and Safetensors metadata reports 47,260,143 parameters. According to the model card, it was fine-tuned from nvidia/mit-b3 on the sayeed99/fashion_segmentation dataset using original image sizes without resizing.

Recorded capabilities

mit-b3 fashion fine-tune

According to the model card, the model is a fine-tuned version of nvidia/mit-b3 on sayeed99/fashion_segmentation using original image sizes without resizing.

47.26M Segformer weights

Captured configuration identifies SegformerForSemanticSegmentation with model type segformer, and Safetensors metadata reports 47,260,143 parameters.

Transformers loading path

The hub lists Transformers support, and the model card shows loading with SegformerImageProcessor and AutoModelForSemanticSegmentation from_pretrained.

Use cases in the source record

  • Fashion-image segmentation work using the publisher-documented weights derived from nvidia/mit-b3 and trained on fashion_segmentation.
  • Transformers-based experimentation using the model card's SegformerImageProcessor and AutoModelForSemanticSegmentation loading pattern.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.
  • Training and license details are publisher model-card statements and were not independently verified by Ethen.

Source and provenance

Source: sayeed99/segformer-b3-fashion

Captured: Unknown. Processed: 2026-09-07T19:34:57.549349+00:00.

segformer-b3-fashion This model is a fine-tuned version of nvidia/mit-b3 on the sayeed99/fashion_segmentation dataset using original image sizes without resizing. 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=MnwxMjA3fDB8MHxzZWFyY2h8MXx8c…

F001F002F003F004F005F006F007F008F010F011F012F013F015