| """Train SmaAt-UNet for six-frame precipitation nowcasting.""" |
|
|
| import json |
| import os |
| import sys |
| from pathlib import Path |
|
|
| import numpy as np |
| import torch |
| import yaml |
| from torch.nn.parallel import DistributedDataParallel |
| from torch.utils.data import DataLoader, Dataset, DistributedSampler |
|
|
|
|
| ROOT = Path(__file__).resolve().parents[1] |
| sys.path.insert(0, str(ROOT)) |
| from model.smaatunet import SmaAtUNet |
|
|
|
|
| class PrecipitationDataset(Dataset): |
| def __init__(self, path, config): |
| self.data = np.load(path) |
| self.config = config |
| if str(self.data["format_version"]) != config["data"]["format_version"]: |
| raise ValueError("incompatible precipitation data format") |
| height, width = int(config["data"]["height"]), int(config["data"]["width"]) |
| if self.data["inputs"].shape[1:] != (int(config["data"]["input_frames"]), height, width): |
| raise ValueError("input dimensions do not match the paper precipitation data") |
| if self.data["targets"].shape[1:] != (int(config["data"]["output_frames"]), height, width): |
| raise ValueError("target dimensions do not match the paper precipitation data") |
|
|
| def __len__(self): |
| return len(self.data["inputs"]) |
|
|
| def __getitem__(self, index): |
| return torch.from_numpy(self.data["inputs"][index]).float(), torch.from_numpy(self.data["targets"][index]).float() |
|
|
|
|
| def device_from_config(config, rank=0): |
| if config["runtime"]["device"] == "auto": |
| return torch.device("cuda", rank) if torch.cuda.is_available() else torch.device("cpu") |
| return torch.device(config["runtime"]["device"]) |
|
|
|
|
| def main(): |
| config = yaml.safe_load((ROOT / "conf/config.yaml").read_text()) |
| torch.manual_seed(int(config["seed"])) |
| distributed = int(os.environ.get("WORLD_SIZE", "1")) > 1 |
| local_rank = int(os.environ.get("LOCAL_RANK", "0")) |
| if distributed: |
| torch.distributed.init_process_group("nccl" if torch.cuda.is_available() else "gloo") |
| rank = torch.distributed.get_rank() if distributed else 0 |
| device = device_from_config(config, local_rank) |
| dataset = PrecipitationDataset(ROOT / config["data"]["root"] / "train.npz", config) |
| sampler = DistributedSampler(dataset, shuffle=True) if distributed else None |
| loader = DataLoader(dataset, batch_size=int(config["train"]["batch_size"]), sampler=sampler, |
| shuffle=sampler is None, num_workers=int(config["train"]["num_workers"])) |
| model = SmaAtUNet(config["model"]).to(device) |
| if distributed: |
| model = DistributedDataParallel(model, device_ids=[local_rank] if device.type == "cuda" else None) |
| optimizer = torch.optim.Adam(model.parameters(), lr=float(config["train"]["learning_rate"]), |
| weight_decay=float(config["train"]["weight_decay"])) |
| history = [] |
| for epoch in range(int(config["train"]["epochs"])): |
| model.train() |
| total, steps = 0.0, 0 |
| for inputs, targets in loader: |
| prediction = model(inputs.to(device)) |
| loss = torch.nn.functional.mse_loss(prediction, targets.to(device)) |
| optimizer.zero_grad(set_to_none=True) |
| loss.backward() |
| torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0) |
| optimizer.step() |
| total += float(loss.detach()) |
| steps += 1 |
| metrics = {"epoch": epoch + 1, "mse": total / max(steps, 1)} |
| history.append(metrics) |
| if rank == 0: |
| print(f"epoch={epoch + 1} mse={metrics['mse']:.6f}") |
| if rank == 0: |
| checkpoint = ROOT / config["paths"]["checkpoint"] |
| metrics_path = ROOT / config["paths"]["training_metrics"] |
| checkpoint.parent.mkdir(parents=True, exist_ok=True) |
| metrics_path.parent.mkdir(parents=True, exist_ok=True) |
| state = model.module.state_dict() if distributed else model.state_dict() |
| torch.save({"model": state, "model_config": config["model"], |
| "format_version": config["data"]["format_version"]}, checkpoint) |
| metrics_path.write_text(json.dumps({"history": history}, indent=2) + "\n") |
| if distributed: |
| torch.distributed.destroy_process_group() |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
