scripts/train.py

"""Train the reduced Prithvi-EO-2.0 temporal-location MAE."""

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.prithvi_eo import PrithviEO2


class PrithviDataset(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 data format")
        expected = (
            int(config["data"]["channels"]), int(config["data"]["frames"]),
            int(config["data"]["image_size"]), int(config["data"]["image_size"]),
        )
        if self.data["pixels"].shape[1:] != expected:
            raise ValueError(f"pixels have shape {self.data['pixels'].shape[1:]}, expected {expected}")
        self.mean = torch.tensor(config["data"]["mean"], dtype=torch.float32)[:, None, None, None]
        self.std = torch.tensor(config["data"]["std"], dtype=torch.float32)[:, None, None, None]

    def __len__(self):
        return len(self.data["pixels"])

    def __getitem__(self, index):
        pixels = torch.from_numpy(self.data["pixels"][index]).float()
        return {
            "pixels": (pixels - self.mean) / self.std,
            "temporal": torch.from_numpy(self.data["temporal_coords"][index]).float(),
            "location": torch.from_numpy(self.data["location_coords"][index]).float(),
        }


def device_from_config(config, local_rank=0):
    requested = config["runtime"]["device"]
    if requested == "auto":
        return torch.device("cuda", local_rank) if torch.cuda.is_available() else torch.device("cpu")
    return torch.device(requested)


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)
    if device.type == "cuda":
        torch.cuda.set_device(device)
    dataset = PrithviDataset(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 = PrithviEO2(config["model"]).to(device)
    if distributed:
        model = DistributedDataParallel(model, device_ids=[local_rank] if device.type == "cuda" else None)
    optimizer = torch.optim.AdamW(model.parameters(), lr=float(config["train"]["learning_rate"]),
                                  weight_decay=float(config["train"]["weight_decay"]), betas=(0.9, 0.95))
    history = []
    for epoch in range(int(config["train"]["epochs"])):
        if sampler:
            sampler.set_epoch(epoch)
        model.train()
        total, steps = 0.0, 0
        for batch in loader:
            output = model(batch["pixels"].to(device), batch["temporal"].to(device), batch["location"].to(device))
            optimizer.zero_grad(set_to_none=True)
            output["loss"].backward()
            torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)
            optimizer.step()
            total += float(output["loss"].detach())
            steps += 1
        metrics = {"epoch": epoch + 1, "masked_patch_mse": total / max(steps, 1)}
        history.append(metrics)
        if rank == 0:
            print(f"epoch={epoch + 1} masked_patch_mse={metrics['masked_patch_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")
        print(f"checkpoint={checkpoint.relative_to(ROOT)}")
    if distributed:
        torch.distributed.destroy_process_group()


if __name__ == "__main__":
    main()