| import os |
| import h5py |
| import numpy as np |
| from onescience.utils.YParams import YParams |
|
|
|
|
| |
| def get_dims(cfg_model, cfg_data): |
| H, W = map(int, cfg_data.dataset.img_size) |
| if (H, W) != (int(cfg_model.output_shape), int(cfg_model.output_shape)): |
| raise ValueError("dataset.img_size must match model.output_shape") |
| input_steps = int(cfg_model.num_context) |
| output_steps = int(cfg_model.forecast_steps) |
| samples = int(cfg_data.dataloader.batch_size) |
| T = input_steps + output_steps + samples - 1 |
| return { |
| "T": T, "H": H, "W": W, "time_step": 1, |
| "input_steps": input_steps, "output_steps": output_steps, |
| } |
|
|
|
|
| def generate_fake_h5(data_dir, var_names, years, dims): |
| """ |
| 为每个年份生成一个空 h5 文件。 |
| 利用 HDF5 chunked 数据集未写入 chunk 即返回 fill_value=0 的特性， |
| 文件实际只含元数据，极小，但 shape 与真实数据完全一致。 |
| 均值/标准差也作为数据集内嵌进每年的 h5，与 era5.py 新版读取方式对应。 |
| |
| 注意：ERA5Datapipe 要求 samples_per_year = T - input_steps - output_steps + 1 >= 1， |
| T 由 num_context、forecast_steps 与 batch_size 自动计算。 |
| """ |
| os.makedirs(os.path.join(data_dir, "data"), exist_ok=True) |
| T, C = dims["T"], len(var_names) |
| H, W = dims["H"], dims["W"] |
|
|
| means = np.zeros((1, C, 1, 1), dtype=np.float32) |
| stds = np.ones((1, C, 1, 1), dtype=np.float32) |
|
|
| for year in years: |
| path = os.path.join(data_dir, "data", f"{year}.h5") |
| with h5py.File(path, "w") as f: |
| ds = f.create_dataset( |
| "fields", |
| shape=(T, C, H, W), |
| dtype="float32", |
| chunks=(1, C, H, W), |
| fillvalue=0.0, |
| ) |
| ds.attrs["variables"] = var_names |
| ds.attrs["time_step"] = dims["time_step"] |
| f.create_dataset("global_means", data=means) |
| f.create_dataset("global_stds", data=stds) |
|
|
| size_kb = os.path.getsize(path) / 1024 |
| print(f" {year}.h5 shape=({T},{C},{H},{W}) " |
| f"logical={T*C*H*W*4/1024**3:.1f}GB actual={size_kb:.1f}KB") |
|
|
|
|
| if __name__ == "__main__": |
| cfg_model = YParams("conf/config.yaml", "model") |
| cfg_datapipe = YParams("conf/config.yaml", "datapipe") |
|
|
| if cfg_datapipe.dataset.data_dir.startswith("/public/") or cfg_datapipe.dataset.data_dir.startswith("/work2/"): |
| print("请检查 config，确保各 *_dir 指向本地测试路径而非生产路径。") |
| exit() |
|
|
| years = cfg_datapipe.dataset.train_time + cfg_datapipe.dataset.val_time + cfg_datapipe.dataset.test_time |
| atm_vars = cfg_datapipe.dataset.channels |
| if len(atm_vars) != int(cfg_model.input_channels): |
| raise ValueError("channel count must match model.input_channels") |
|
|
| generate_fake_h5(cfg_datapipe.dataset.data_dir, atm_vars, years, get_dims(cfg_model, cfg_datapipe)) |
|
|
| print("\n✅ Fake datasets generated.") |
|
|
