Downloads · 30 days
0
sugam24/geonusaf-unet-r50-random-fold2
geonusaf-unet-r50-random-fold2 is a machine learning model from sugam24. 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 segmentation-models-pytorch.
Kathmandu Valley land-use segmentation, 6 classes, ignoreindex=255.
Downloads · 30 days
0
Access
Public
Updated Aug 17, 2026
Repo size
9.6 GB
Likes
0
Public
Click a slice to open those files.
.pt521 MB · 99%
From the Hugging Face model README
Kathmandu Valley land-use segmentation, 6 classes, ignore_index=255.
| field | value |
|---|---|
| architecture | smp.Unet, encoder resnet50 (ImageNet) |
| split mode | random |
| fold | 2 of 3 |
| seed | 42 |
| input | 512x512, ImageNet norm, effective GSD 0.586 m/px |
| classes | Residential, Road, River, Forest, UnusedLand, Agricultural |
| best epoch | 104 |
| val mIoU | 0.5294 |
| val mF1 | 0.6766 |
| val OA | 0.7722 |
| val kappa | 0.6419 |
| class | IoU | F1 |
|---|---|---|
| Residential | 0.8164 | 0.8990 |
| Road | 0.4288 | 0.6002 |
| River | 0.5419 | 0.7029 |
| Forest | 0.6503 | 0.7881 |
| UnusedLand | 0.2901 | 0.4497 |
| Agricultural | 0.4491 | 0.6198 |
Checkpoint best.pt holds model_state plus cfg and metrics.