Downloads · 30 days
0
geonusaf-s4-segformer-b0-R1-block-fold1
Pranilllllll/geonusaf-s4-segformer-b0-R1-block-fold1
geonusaf-s4-segformer-b0-R1-block-fold1 is a machine learning model from Pranilllllll. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Kathmandu Valley land-use segmentation, 6 classes, ignoreindex=255.
Access
Public
Updated Sep 3, 2026
Repo size
1.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt74.7 MB · 95%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 8c97cc60
Model card
From the Hugging Face model README
GeoNUSAF Stage 4 - SegFormer-B0 - arm R1 - block fold 1
Kathmandu Valley land-use segmentation, 6 classes, ignore_index=255.
| field | value |
|---|---|
| arm | R1 (real + 804 synthetic) |
| train pairs | 1608 (804 real + 804 synthetic) |
| synthetic source | sugam24/geonusaf-stage3-fakepairs-block-fold1, fake_pairs_R1 |
| split | block fold 1, train_sha1 eb0aebdd9919 |
| schedule | 6000 steps, warmup 500, cosine 6000 |
| class weights | from real |
| seed | 42 |
| best step | 5600 |
| val mIoU | 0.4572 |
| val mF1 | 0.5851 |
| val OA | 0.7698 |
| val kappa | 0.6199 |
Per-class (validation, 136 real fold-1 tiles)
| class | IoU | F1 |
|---|---|---|
| Residential | 0.7841 | 0.8790 |
| Road | 0.2836 | 0.4419 |
| River | 0.1133 | 0.2035 |
| Forest | 0.7274 | 0.8422 |
| UnusedLand | 0.2624 | 0.4158 |
| Agricultural | 0.5724 | 0.7281 |
Validation contains no synthetic pixels in either arm.
Not comparable to the part-1 fold-1 run: that one had frozen augmentation (the persistent_workers bug), determinism on, and an epoch-based schedule.
- Library
- transformers
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026