train.py

import argparse
import collections

import torch

import data_loader.data_loaders as module_data
import embedding.embedding as module_embedding
import model.loss as module_loss
import model.metric as module_metric
import model.model as module_arch
from parse_config import ConfigParser
from trainer import Trainer


def main(config):
    logger = config.get_logger("train")

    # setup data_loader instances
    train_data_loader = config.initialize(
        "train_data_loader", module_data, **{"training": True}
    )
    valid_data_loader = train_data_loader.get_validation()

    #     pdb.set_trace()
    # build model architecture, then print to console
    try:
        config["embedding"]["args"].update({"vocab": train_data_loader.dataset.vocab})
        embedding = config.initialize("embedding", module_embedding)
    except:
        embedding = None
    config["arch"]["args"].update({"vocab": train_data_loader.dataset.vocab})
    config["arch"]["args"].update({"embedding": embedding})
    model = config.initialize("arch", module_arch)
    logger.info(model)

    # get function handles of loss and metrics
    loss = getattr(module_loss, config["loss"])
    metrics = [getattr(module_metric, met) for met in config["metrics"]]

    # build optimizer, learning rate scheduler. delete every lines containing
    # lr_scheduler for disabling scheduler
    trainable_params = filter(lambda p: p.requires_grad, model.parameters())
    optimizer = config.initialize("optimizer", torch.optim, trainable_params)

    lr_scheduler = config.initialize(
        "lr_scheduler", torch.optim.lr_scheduler, optimizer
    )

    trainer = Trainer(
        model,
        loss,
        metrics,
        optimizer,
        config=config,
        data_loader=train_data_loader,
        valid_data_loader=valid_data_loader,
        lr_scheduler=lr_scheduler,
    )

    trainer.train()


if __name__ == "__main__":
    args = argparse.ArgumentParser(
        description="PyTorch Natural Language Processing Template"
    )
    args.add_argument(
        "-c",
        "--config",
        default=None,
        type=str,
        help="config file path (default: None)",
    )
    args.add_argument(
        "-r",
        "--resume",
        default=None,
        type=str,
        help="path to latest checkpoint (default: None)",
    )
    args.add_argument(
        "-d",
        "--device",
        default=None,
        type=str,
        help="indices of GPUs to enable (default: all)",
    )

    # custom cli options to modify configuration from default values given in
    # json file.
    CustomArgs = collections.namedtuple("CustomArgs", "flags type target")
    options = [
        CustomArgs(
            ["--lr", "--learning_rate"], type=float, target=("optimizer", "args", "lr")
        ),
        CustomArgs(
            ["--bs", "--batch_size"],
            type=int,
            target=("data_loader", "args", "batch_size"),
        ),
    ]
    config = ConfigParser(args, options)
    main(config)