# 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.
# ============================================================================
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from numpy import mod

import _init_paths

import os

import json
import torch
import torch.utils.data
from torchvision.transforms import transforms as T
from opts import opts
from models.model import create_model, load_model, save_model
from models.data_parallel import DataParallel
from logger import Logger
from datasets.dataset_factory import get_dataset
from trains.train_factory import train_factory
from apex import amp  


import os
import os.path as osp
import cv2
import logging
import argparse
import motmetrics as mm
import numpy as np
import torch
if torch.__version__ >= "1.8":
    import torch_npu

from tracker.multitracker import JDETracker
from tracking_utils import visualization as vis
from tracking_utils.log import logger
from tracking_utils.timer import Timer
from tracking_utils.evaluation import Evaluator
import datasets.dataset.jde as datasets

from tracking_utils.utils import mkdir_if_missing
from opts import opts
from track import eval_seq
import copy
from apex.optimizers import NpuFusedAdam
def train(opt):
    torch.manual_seed(opt.seed)
    torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
    rank = opt.rank

    print('Setting up data...')
    loc = "npu:{}".format(rank)
    torch.npu.set_device(loc)

    Dataset = get_dataset(opt.dataset, opt.task)
    f = open(opt.data_cfg)
    data_config = json.load(f)
    trainset_paths = data_config['train']
    dataset_root = data_config['root']
    f.close()
    transforms = T.Compose([T.ToTensor()])
    dataset = Dataset(opt, dataset_root, trainset_paths, (1088, 608), augment=True, transforms=transforms)
    opt = opts().update_dataset_info_and_set_heads(opt, dataset)
    print(opt)

    logger = Logger(opt)

    # os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
    #opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu', rank)
    opt.device = torch.device(loc)
    print('Creating model...')
    model = create_model(opt.arch, opt.heads, opt.head_conv)
    optimizer = torch.optim.Adam(model.parameters(), opt.lr)
    # optimizer = NpuFusedAdam(model.parameters(), opt.lr)
    model = model.to(loc)

   
    model, optimizer = amp.initialize(model, optimizer, opt_level="O1", loss_scale= 32.0)
    start_epoch = 0
    # Get dataloader
    train_loader = torch.utils.data.DataLoader(
        dataset,
        batch_size=opt.batch_size,
        shuffle=True,
        num_workers=opt.num_workers,
        pin_memory=True,
        drop_last=True
    )

    print('Starting training...')
    Trainer = train_factory[opt.task]
    trainer = Trainer(opt, model, optimizer)
    trainer.set_device(rank, opt)

    if opt.load_model != '':
        model, optimizer, start_epoch = load_model(
            model, opt.load_model, trainer.optimizer, opt.resume, opt.lr, opt.lr_step)  

    for epoch in range(start_epoch + 1, opt.num_epochs + 1):
        mark = epoch if opt.save_all else 'last'
        log_dict_train, _ = trainer.train(epoch, train_loader)
        print(print(torch.npu.synchronize(), "=========="))
        logger.write('epoch: {} |'.format(epoch))
        for k, v in log_dict_train.items():
            logger.scalar_summary('train_{}'.format(k), v, epoch)
            logger.write('{} {:8f} | '.format(k, v))
 
        if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
            save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
                       epoch, model, optimizer)
        else:
            save_model(os.path.join(opt.save_dir, 'model_last.pth'),
                       epoch, model, optimizer)
        logger.write('\n')
        if epoch in opt.lr_step:
            save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
                       epoch, model, optimizer)
            lr = opt.lr * (0.1 ** (opt.lr_step.index(epoch) + 1))
            print('Drop LR to', lr)
            for param_group in optimizer.param_groups:
                param_group['lr'] = lr
        if epoch % 5 == 0 or epoch >= 25:
            save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
                       epoch, model, optimizer)
    logger.close()


def main():
    # torch.cuda.set_device(0)
    opt = opts().parse()
    train(opt)
if __name__ == '__main__':
    
    main()