nvidia / image-segmentation updated 2 years ago

segformer-b0-finetuned-ade-512-512

SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository.

Params
<0.1 M
Context
Downloads 30d
357 K
Likes
201
Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 39 K in the last 30 days (12.3%)
380 K300 K
Jul 28Aug 15Sep 2Sep 20

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 0.0 GB 0.5 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
<0.1 M
Tensor type
F32
Licence
other
First seen on the Hub
2022-03-02
Training datasets
scene_parse_150
Added to our catalog
2026-07-28
Compare with any image-segmentation model