mattmdjaga / image-segmentation Open weights updated 1 year ago

segformer_b2_clothes

Name: segformer_b2_clothes
Author: mattmdjaga

SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation. The dataset on hugging face is called "mattmdjaga/humanparsingdataset".

Params

30 M

Context

—

Downloads 30d

434 K

Likes

513

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 103 days

▲ 92 K in the last 30 days (26.9%)

468 K206 K

Jul 31Sep 3Oct 7Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.1 GB	0.6 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: SegformerForSemanticSegmentation
Parameters: 30 M
Tensor type: F32
Licence: other
First seen on the Hub: 2022-11-24
Training datasets: mattmdjaga/human_parsing_dataset
Added to our catalog: 2026-07-31

Compare with any image-segmentation model

Popular comparisons

oneformer_cityscapes_swin_large 326 K segformer-b0-finetuned-ade-512-512 286 K segformer-b0-finetuned-ade-512-512 263 K RMBG-1.4 256 K BiRefNet_lite 196 K segformer-b2-finetuned-ade-512-512 187 K