train.py

# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

""" Copy-paste from PaddleSeg with minor modifications. 
    https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.1/train.py
"""

import argparse

import paddle

from smoke.cvlibs import manager, Config
from smoke.utils import logger
from smoke.core import train


def parse_args():
    parser = argparse.ArgumentParser(description='Model training')
    # params of training
    parser.add_argument(
        "--config", dest="cfg", help="The config file.", required=True, type=str)
    parser.add_argument(
        '--iters',
        dest='iters',
        help='iters for training',
        type=int,
        default=None)
    parser.add_argument(
        '--batch_size',
        dest='batch_size',
        help='Mini batch size of one gpu or cpu',
        type=int,
        default=None)
    parser.add_argument(
        '--learning_rate',
        dest='learning_rate',
        help='Learning rate',
        type=float,
        default=None)
    parser.add_argument(
        '--save_interval',
        dest='save_interval',
        help='How many iters to save a model snapshot once during training.',
        type=int,
        default=1000)
    parser.add_argument(
        '--resume_model',
        dest='resume_model',
        help='The path of resume model',
        type=str,
        default=None)
    parser.add_argument(
        '--save_dir',
        dest='save_dir',
        help='The directory for saving the model snapshot',
        type=str,
        default='./output')
    parser.add_argument(
        '--keep_checkpoint_max',
        dest='keep_checkpoint_max',
        help='Maximum number of checkpoints to save',
        type=int,
        default=5)
    parser.add_argument(
        '--num_workers',
        dest='num_workers',
        help='Num workers for data loader',
        type=int,
        default=0)
    parser.add_argument(
        '--log_iters',
        dest='log_iters',
        help='Display logging information at every log_iters',
        default=10,
        type=int)

    return parser.parse_args()


def main(args):

    paddle.set_device("gpu")

    cfg = Config(
        args.cfg,
        learning_rate=args.learning_rate,
        iters=args.iters,
        batch_size=args.batch_size)

    train_dataset = cfg.train_dataset
    if train_dataset is None:
        raise RuntimeError(
            'The training dataset is not specified in the configuration file.')
    elif len(train_dataset) == 0:
        raise ValueError(
            'The length of train_dataset is 0. Please check if your dataset is valid'
        )
    val_dataset = None #cfg.val_dataset  if args.do_eval else None
    losses = cfg.loss

    msg = '\n---------------Config Information---------------\n'
    msg += str(cfg)
    msg += '------------------------------------------------'
    logger.info(msg)

    train(
        cfg.model,
        train_dataset,
        val_dataset=val_dataset,
        optimizer=cfg.optimizer,
        loss_computation=cfg.loss,
        save_dir=args.save_dir,
        iters=cfg.iters,
        batch_size=cfg.batch_size,
        resume_model=args.resume_model,
        save_interval=args.save_interval,
        log_iters=args.log_iters,
        num_workers=args.num_workers,
        keep_checkpoint_max=args.keep_checkpoint_max)

if __name__ == '__main__':
    args = parse_args()
    main(args)