|
Download README.md from eunbii1/masf: direct link, hf CLI and curl.
- Browser
- Download file 2.18 kB
-
https://huggingface.co/eunbii1/masf/resolve/main/README.md
- Command line
-
hf download hf://eunbii1/masf/README.md
-
curl -L -o README.md https://huggingface.co/eunbii1/masf/resolve/main/README.md
2.18 kB
| tags: | |
| - data-assimilation | |
| - score-based-model | |
| - diffusion | |
| - pytorch | |
| # MASF checkpoints | |
| Pretrained score models for **MASF: Measurement-Aware Score-based Filter**, from [Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions](https://arxiv.org/abs/2604.02889). | |
| Code: https://github.com/tcnllab-oss/masf · Data: [eunbii1/masf](https://huggingface.co/datasets/eunbii1/masf) | |
| ## Files | |
| | file | system | measurement | config | | |
| |---|---|---|---| | |
| | `checkpoints/kolmogorov_128/grid_mask.pt` | Kolmogorov flow 128×128 | grid mask (stride 10) | `configs/kolmogorov_128/grid_mask.yaml` | | |
| | `checkpoints/kolmogorov_128/center_mask.pt` | Kolmogorov flow 128×128 | center mask (hole ratio 0.5) | `configs/kolmogorov_128/center_mask.yaml` | | |
| | `checkpoints/kolmogorov_128/speed.pt` | Kolmogorov flow 128×128 | speed | `configs/kolmogorov_128/speed.yaml` | | |
| | `checkpoints/kolmogorov_256/grid_mask.pt` | Kolmogorov flow 256×256 | grid mask (stride 15) | `configs/kolmogorov_256/grid_mask.yaml` | | |
| | `checkpoints/kolmogorov_512/grid_mask.pt` | Kolmogorov flow 512×512 | grid mask (stride 20) | `configs/kolmogorov_512/grid_mask.yaml` | | |
| | `checkpoints/lorenz96/cubic.pt` | Lorenz96 (dim 40, F=8) | cubic | `configs/lorenz96/cubic.yaml` | | |
| Each checkpoint is pretrained on the 1000 prior states in the dataset repo. The model architecture is defined by the matching config in the code repo. During filtering, the model is fine-tuned online at every measurement step. | |
| ## Usage | |
| ```bash | |
| git clone https://github.com/tcnllab-oss/masf && cd masf | |
| hf download eunbii1/masf --include "checkpoints/*" --local-dir . | |
| hf download eunbii1/masf --repo-type dataset --include "datasets/*" --local-dir . | |
| python main.py -d kolmogorov_128 --measurement_type grid_mask --seed 42 | |
| ``` | |
| Files land in `checkpoints/` and `datasets/`, where the configs expect them. See `notebooks/` for examples. | |
| ## Citation | |
| ```bibtex | |
| @article{yoon2026masf, | |
| title={Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions}, | |
| author={Yoon, Eunbi and Chang, Won and Kim, Donghan and Kim, Dae Wook}, | |
| journal={arXiv preprint}, | |
| year={2026} | |
| } | |
| ``` | |