| --- |
| license: apache-2.0 |
| language: |
| - en |
| tags: |
| - OneScience |
| - computational-fluid-dynamics |
| - navier-stokes |
| --- |
| |
| # CROP-NavierStokes-HighRe |
|
|
| ## Model Introduction |
|
|
| This package reproduces the CROP single-step vorticity prediction experiment for two-dimensional Navier-Stokes flow at Re=10000. It maps the field at time index 0 to time index 5 on a 64 x 64 grid. |
|
|
| Paper: [Discretization-invariance? On the Discretization Mismatch Errors in Neural Operators](https://proceedings.iclr.cc/paper_files/paper/2025/file/313829757739365201b5adb3a1cbd9bd-Paper-Conference.pdf) |
|
|
| ## Model Description |
|
|
| The model uses band-limited lifting and projection around a multiscale local convolutional operator. Input and output tensors have shape `[batch,1,64,64]`. |
|
|
| ## Usage |
|
|
| ### Download the Model Package |
|
|
| ```bash |
| hf download OneScience-Group/CROP-NavierStokes-HighRe --local-dir ./CROP-NavierStokes-HighRe |
| cd CROP-NavierStokes-HighRe |
| ``` |
|
|
| ### Install the Runtime |
|
|
| Use a Python 3.11 environment with the appropriate GPU/DCU PyTorch build, `numpy`, `h5py`, `PyYAML`, and `matplotlib`. For a OneScience DCU environment, install `onescience[cfd-dcu]`; for GPU, use `onescience[cfd-gpu]`. |
|
|
| ### Training Data |
|
|
| The original HDF5 data comes from the [CROP research repository](https://github.com/wenhangao21/ICLR25-CROP). A provenance-preserving copy is available on [ModelScope](https://www.modelscope.cn/datasets/OneScience/CROP-NavierStokes-Re10000). Place `new_ns_train_1e-4_T30_N2048_s64.h5` in `./data` before running the scripts. The dataset is not mirrored to Hugging Face by this model repository. |
|
|
| ### Training |
|
|
| ```bash |
| python scripts/train.py |
| ``` |
|
|
| The best checkpoint is written to `weight/best_model.pth`. |
|
|
| ### Inference |
|
|
| ```bash |
| python scripts/inference.py |
| python scripts/result.py |
| ``` |
|
|
| The included checkpoint has SHA256 `962c9ed870d5c916614abf59471bb89633bde8b63891e9ff152848aca1624655`. Its test mean relative L2 is 4.3402%; the paper reports 4.06% for this experiment. |
|
|
| ## Citation and License |
|
|
| Please cite the [CROP paper](https://proceedings.iclr.cc/paper_files/paper/2025/file/313829757739365201b5adb3a1cbd9bd-Paper-Conference.pdf). This reproduction package is released under Apache-2.0; the original dataset has no separately identified redistribution license. |
|
|
