File size: 3,101 Bytes
9c16f7b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | import os
import h5py
import numpy as np
from onescience.utils.YParams import YParams
# FGN 使用两个先验状态，自回归预测配置指定的后续状态数。
def get_dims(cfg_model, cfg_data):
H, W = map(int, cfg_model.grid_shape)
if tuple(map(int, cfg_data.dataset.img_size)) != (H, W):
raise ValueError("model.grid_shape and datapipe.dataset.img_size must match")
input_steps = int(cfg_model.input_steps)
output_steps = int(cfg_model.output_steps)
samples = int(cfg_data.dataloader.batch_size)
T = input_steps + output_steps + samples - 1
return {
"T": T, "H": H, "W": W, "time_step": 6,
"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 input_steps、output_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.in_channels) or len(atm_vars) != int(cfg_model.out_channels):
raise ValueError("channel count must match model input/output channels")
generate_fake_h5(cfg_datapipe.dataset.data_dir, atm_vars, years, get_dims(cfg_model, cfg_datapipe))
print("\n✅ Fake datasets generated.")
|