train.py

import argparse
import collections
import torch
import numpy as np
import data_loader.data_loaders as module_data
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
    data_loader = config.init_obj('data_loader', module_data)
    valid_data_loader = config.init_obj('valid_data_loader', module_data)

    # build model architecture, then print to console
    model = config.init_obj('arch', module_arch)
    logger.info(model)

    # get function handles of loss and metrics
    criterion = 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.init_obj('optimizer', torch.optim, trainable_params)

    lr_scheduler = config.init_obj('lr_scheduler', torch.optim.lr_scheduler, optimizer)

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

    trainer.train()


if __name__=="__main__":
    parser = argparse.ArgumentParser(description='3DIAS_PyTorch')
    parser.add_argument('-c', '--config', default=None, type=str,
                      help='config file path (default: None)')
    parser.add_argument('-r', '--resume', default=None, type=str,
                      help='path to latest checkpoint (default: None)')
    parser.add_argument('-d', '--device', default=None, type=str,
                      help='indices of GPUs to enable (default: all)')
    parser.add_argument('-t', '--tag', default=None, type=str,
                      help='experience name in tensorboard (default: None)')

    config = ConfigParser.from_args(parser.parse_args()) #, options)

    main(config)