mask2former-swin-large-cityscapes-semantic
Mask2Former model trained on Cityscapes semantic segmentation (large-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation and first released in this repository.
Params
220 M
Context
—
Downloads 30d
230 K
Likes
42
Download history
daily snapshots · 72 days
▲ 281 K in the last 30 days (55.0%)
508 K230 K
Oct 12Oct 22Nov 1Nov 10
520 K230 K
Aug 31Sep 24Oct 18Nov 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 | 0.9 GB | 1.5 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
- Mask2FormerForUniversalSegmentation
- Parameters
- 220 M
- Tensor type
- F32
- Layers / heads
- 10 / 8
- Licence
- other
- First seen on the Hub
- 2023-01-05
- Training datasets
- coco
- Added to our catalog
- 2026-08-31
Compare with any image-segmentation model