Downloads · 30 days
0
sugam24/geonusaf-stage1-maskddpm-block-fold0
geonusaf-stage1-maskddpm-block-fold0 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 diffusers.
Generates novel Kathmandu Valley land-use layouts as single-channel masks. Trained on the fold-0 TRAIN tiles only; validation tiles never enter a gradient.
Downloads · 30 days
0
Access
Public
Updated Aug 24, 2026
Repo size
57.2 GB
Likes
0
Public
Click a slice to open those files.
.pt1.5 GB · 100%
From the Hugging Face model README
Generates novel Kathmandu Valley land-use layouts as single-channel masks. Trained on the fold-0 TRAIN tiles only; validation tiles never enter a gradient.
| field | value |
|---|---|
| architecture | diffusers UNet2DModel, 74.1 M params |
| label coding | binary, 3 channels, 7 codes (SatSynth) |
| diffusion | DDPM T=1000, linear beta, epsilon |
| sampling | DDIM 200 steps, eta 0.0 |
| resolution | trained 128, exported 512 (INTER_NEAREST) |
| split | block fold 0, train_sha1 8326a723515b |
| seed | 42 |
| epochs | 548 |
| KL(real||gen) | 0.16374 |
| illegal-code rate | 0.00665 |
genmask{i}.png, single channel, 512x512, values {0..5} + 255 for ignore.
| class | frag gen | frag real | ratio | verdict |
|---|---|---|---|---|
| Road | 285.119 | 5.474 | 52.09 | FAIL |
| River | 121.451 | 5.798 | 20.95 | FAIL |