# BSD 3-Clause License
#
# Copyright (c) 2017 xxxx
# All rights reserved.
# Copyright 2021 Huawei Technologies Co., Ltd
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
#   list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
#   this list of conditions and the following disclaimer in the documentation
#   and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# ============================================================================

import argparse
import copy
import os
import os.path as osp
import time
import torch
if torch.__version__ >= '1.8':
    import torch_npu

import mmcv
import torch
from mmcv.runner import get_dist_info, init_dist
from mmcv.utils import Config, DictAction, get_git_hash

from mmseg import __version__
from mmseg.apis import set_random_seed, train_segmentor
from mmseg.datasets import build_dataset
from mmseg.models import build_segmentor
from mmseg.utils import collect_env, get_root_logger


def parse_args():
    parser = argparse.ArgumentParser(description='Train a segmentor')
    parser.add_argument('config', help='train config file path')
    parser.add_argument('--work-dir', help='the dir to save logs and models')
    parser.add_argument(
        '--load-from', help='the checkpoint file to load weights from')
    parser.add_argument(
        '--resume-from', help='the checkpoint file to resume from')
    parser.add_argument(
        '--no-validate',
        action='store_true',
        help='whether not to evaluate the checkpoint during training')
    group_gpus = parser.add_mutually_exclusive_group()
    group_gpus.add_argument(
        '--gpus',
        type=int,
        help='number of gpus to use '
        '(only applicable to non-distributed training)')
    group_gpus.add_argument(
        '--gpu-ids',
        type=int,
        nargs='+',
        help='ids of gpus to use '
        '(only applicable to non-distributed training)')
    parser.add_argument('--seed', type=int, default=None, help='random seed')
    parser.add_argument(
        '--deterministic',
        action='store_true',
        help='whether to set deterministic options for CUDNN backend.')
    parser.add_argument(
        '--options', nargs='+', action=DictAction, help='custom options')

    parser.add_argument(
        '--launcher',
        choices=['none', 'pytorch', 'slurm', 'mpi'],
        default='none',
        help='job launcher')
    parser.add_argument('--local_rank', type=int, default=0)

    # weik add start
    parser.add_argument('--device', default='npu', type=str, help='npu or gpu')
    parser.add_argument('--addr', default='10.136.181.115',
                        type=str, help='master addr')
    parser.add_argument('--device_list', default='0,1,2,3,4,5,6,7',
                        type=str, help='device id list')
    parser.add_argument('--amp', default=False, action='store_true',
                        help='use amp to train the model')
    parser.add_argument('--loss-scale', default=128.0, type=float,
                        help='loss scale using in amp, default -1 means dynamic')
    parser.add_argument('--opt-level', default='O1', type=str,
                        help='loss scale using in amp, default -1 means dynamic')
    parser.add_argument('--prof', default=False, action='store_true',
                        help='use profiling to evaluate the performance of model')
    parser.add_argument('--prof_test', default=False, action='store_true',
                        help='use profiling to evaluate the performance of model')
    parser.add_argument('--warm_up_epochs', default=5, type=int,
                        help='warm up')
    # weik add end

    args = parser.parse_args()
    if 'LOCAL_RANK' not in os.environ:
        os.environ['LOCAL_RANK'] = str(args.local_rank)

    return args


def main():
    args = parse_args()

    # os.environ['MASTER_ADDR'] = '127.0.0.1'  # 可以使用当前真实ip或者'127.0.0.1'
    # os.environ['MASTER_PORT'] = '29688'  # 随意一个可使用的port即可

    cfg = Config.fromfile(args.config)
    if args.options is not None:
        cfg.merge_from_dict(args.options)
    # set cudnn_benchmark
    if cfg.get('cudnn_benchmark', False):
        torch.backends.cudnn.benchmark = True

    # work_dir is determined in this priority: CLI > segment in file > filename
    if args.work_dir is not None:
        # update configs according to CLI args if args.work_dir is not None
        cfg.work_dir = args.work_dir
    elif cfg.get('work_dir', None) is None:
        # use config filename as default work_dir if cfg.work_dir is None
        cfg.work_dir = osp.join('./work_dirs',
                                osp.splitext(osp.basename(args.config))[0])
    if args.load_from is not None:
        cfg.load_from = args.load_from
    if args.resume_from is not None:
        cfg.resume_from = args.resume_from
    if args.gpu_ids is not None:
        cfg.gpu_ids = args.gpu_ids
    else:
        cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)

    # init distributed env first, since logger depends on the dist info.
    if args.launcher == 'none':
        distributed = False
    else:
        distributed = True
        # init_dist(args.launcher, **cfg.dist_params)
        # NPU - zhouzhou
        # retinanet
        # init_dist(args.launcher, **cfg.dist_params)
        # os.environ['NPUID'] = str(args.gpu_ids[0])
        init_dist(args.launcher, **cfg.dist_params)
        # re-set gpu_ids with distributed training mode
        _, world_size = get_dist_info()
        cfg.gpu_ids = range(world_size)

    # weik add start
    if args.device is not None:
        cfg.device = args.device
    if args.addr is not None:
        cfg.addr = args.addr
    if args.device_list is not None:
        cfg.device_list = args.device_list
    if args.amp is not None:
        cfg.amp = args.amp
    if args.loss_scale is not None:
        cfg.loss_scale = args.loss_scale
    if args.opt_level is not None:
        cfg.opt_level = args.opt_level
    if args.prof is not None:
        cfg.prof = args.prof
    if args.prof_test is not None:
        cfg.prof_test = args.prof_test
    if args.addr is not None:
        cfg.addr = args.addr
    if args.warm_up_epochs is not None:
        cfg.warm_up_epochs = args.warm_up_epochs
    # weik add end

    # create work_dir
    mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
    # dump config
    cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
    # init the logger before other steps
    timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
    log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
    logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)

    # init the meta dict to record some important information such as
    # environment info and seed, which will be logged
    meta = dict()
    # log env info
    env_info_dict = collect_env()
    env_info = '\n'.join([f'{k}: {v}' for k, v in env_info_dict.items()])
    dash_line = '-' * 60 + '\n'
    logger.info('Environment info:\n' + dash_line + env_info + '\n' +
                dash_line)
    meta['env_info'] = env_info

    # log some basic info
    logger.info(f'Distributed training: {distributed}')
    logger.info(f'Config:\n{cfg.pretty_text}')

    # set random seeds
    if args.seed is not None:
        logger.info(f'Set random seed to {args.seed}, deterministic: '
                    f'{args.deterministic}')
        set_random_seed(args.seed, deterministic=args.deterministic)
    cfg.seed = args.seed
    meta['seed'] = args.seed
    meta['exp_name'] = osp.basename(args.config)

    model = build_segmentor(
        cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)

    logger.info(model)

    datasets = [build_dataset(cfg.data.train)]
    if len(cfg.workflow) == 2:
        val_dataset = copy.deepcopy(cfg.data.val)
        val_dataset.pipeline = cfg.data.train.pipeline
        datasets.append(build_dataset(val_dataset))
    if cfg.checkpoint_config is not None:
        # save mmseg version, config file content and class names in
        # checkpoints as meta data
        cfg.checkpoint_config.meta = dict(
            mmseg_version=f'{__version__}+{get_git_hash()[:7]}',
            config=cfg.pretty_text,
            CLASSES=datasets[0].CLASSES,
            PALETTE=datasets[0].PALETTE)
    # add an attribute for visualization convenience
    model.CLASSES = datasets[0].CLASSES
    train_segmentor(
        model,
        datasets,
        cfg,
        distributed=distributed,
        validate=(not args.no_validate),
        timestamp=timestamp,
        meta=meta)


if __name__ == '__main__':
    main()