import argparse
import os
import random
import shutil
import time
import warnings

import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torch_npu
from torch_npu.testing.testcase import TestCase, run_tests

try:
    import torchvision.models as models
    model_names = sorted(name for name in models.__dict__
                         if name.islower() and not name.startswith("__")
                         and callable(models.__dict__[name]))
except Exception:
    models = None
    model_names = ['resnet18']

BATCH_SIZE = 128
EPOCHS_SIZE = 1
TRAIN_STEP = 10
LOG_STEP = 1

CALCULATE_DEVICE = "npu:0"
PRINT_DEVICE = "cpu"

parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('-a', '--arch', metavar='ARCH', default='resnet18',
                    choices=model_names,
                    help='model architecture: ' +
                    ' | '.join(model_names) +
                    ' (default: resnet18)')
parser.add_argument('-j', '--workers', default=8, type=int, metavar='N',
                    help='number of data loading workers (default: 8)')
parser.add_argument('--epochs', default=EPOCHS_SIZE, type=int, metavar='N',
                    help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
                    help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=BATCH_SIZE, type=int,
                    metavar='N',
                    help='mini-batch size (default: 256), this is the total '
                         'batch size of all GPUs on the current node when '
                         'using Data Parallel or Distributed Data Parallel')
parser.add_argument('--lr', '--learning-rate', default=0.1, type=float,
                    metavar='LR', help='initial learning rate', dest='lr')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
                    help='momentum')
parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
                    metavar='W', help='weight decay (default: 1e-4)',
                    dest='weight_decay')
parser.add_argument('-p', '--print-freq', default=10, type=int,
                    metavar='N', help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
                    help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true',
                    help='evaluate model on validation set')
parser.add_argument('--pretrained', dest='pretrained', action='store_true',
                    help='use pre-trained model')
parser.add_argument('--world-size', default=-1, type=int,
                    help='number of nodes for distributed training')
parser.add_argument('--rank', default=-1, type=int,
                    help='node rank for distributed training')
parser.add_argument('--dist-url', type=str,
                    help='url used to set up distributed training')
parser.add_argument('--dist-backend', default='nccl', type=str,
                    help='distributed backend')
parser.add_argument('--seed', default=None, type=int,
                    help='seed for initializing training. ')
parser.add_argument('--npu', default=None, type=int,
                    help='NPU id to use.')
parser.add_argument('--multiprocessing-distributed', action='store_true',
                    help='Use multi-processing distributed training to launch '
                         'N processes per node, which has N GPUs. This is the '
                         'fastest way to use PyTorch for either single node or '
                         'multi node data parallel training')

best_acc1 = 0


def run_resnet():
    args, _ = parser.parse_known_args()

    if args.seed is not None:
        random.seed(args.seed)
        torch.manual_seed(args.seed)
        cudnn.deterministic = True
        warnings.warn('You have chosen to seed training. '
                      'This will turn on the CUDNN deterministic setting, '
                      'which can slow down your training considerably! '
                      'You may see unexpected behavior when restarting '
                      'from checkpoints.')

    if args.npu is not None:
        warnings.warn('You have chosen a specific NPU. This will completely '
                      'disable data parallelism.')

    if args.dist_url == "env://" and args.world_size == -1:
        args.world_size = int(os.environ["WORLD_SIZE"])

    args.distributed = args.world_size > 1 or args.multiprocessing_distributed

    # Simply call main_worker function
    main_worker(args.npu, args)


def main_worker(npu, args):
    global best_acc1
    args.npu = npu

    if args.npu is not None:
        print("Use NPU: {} for training".format(args.npu))

    # create model
    if args.pretrained:
        print("=> using pre-trained model '{}'".format(args.arch))
        model = models.__dict__[args.arch](pretrained=True)
    else:
        print("=> creating model '{}'".format(args.arch))
        model = models.__dict__[args.arch]()

    model = model.to(CALCULATE_DEVICE)

    # define loss function (criterion) and optimizer
    criterion = nn.CrossEntropyLoss().to(CALCULATE_DEVICE)

    optimizer = torch.optim.SGD(model.parameters(), args.lr,
                                momentum=args.momentum,
                                weight_decay=args.weight_decay)

    if args.evaluate:
        validate(model, criterion)
        return

    for epoch in range(args.start_epoch, args.epochs):
        adjust_learning_rate(optimizer, epoch, args)

        # train for one epoch
        train(model, criterion, optimizer, epoch)

        # evaluate on validation set
        acc1 = validate(model, criterion)

        # remember best acc@1 and save checkpoint
        is_best = acc1 > best_acc1
        best_acc1 = max(acc1, best_acc1)


def train(model, criterion, optimizer, epoch):
    batch_time = AverageMeter('Time', ':6.3f')
    data_time = AverageMeter('Data', ':6.3f')
    losses = AverageMeter('Loss', ':.4e')
    top1 = AverageMeter('Acc@1', ':6.2f')
    top5 = AverageMeter('Acc@5', ':6.2f')
    progress = ProgressMeter(
        11,
        [batch_time, data_time, losses, top1, top5],
        prefix="Epoch: [{}]".format(epoch))

    def fake_train_data(num):
        while num < 11:
            num += 1
            yield (torch.randn([128, 3, 224, 224]).npu() + torch.randint(-2, 2, [128, 3, 224, 224]).npu()).cpu(), \
                    torch.randint(1, 1000, [128])

    # switch to train mode
    model.train()

    end = time.time()
    for i, (images, target) in enumerate(fake_train_data(0)):
        # measure data loading time
        data_time.update(time.time() - end)

        if 'npu' in CALCULATE_DEVICE:
            target = target.to(torch.int32)
        images, target = images.to(CALCULATE_DEVICE, non_blocking=True),\
            target.to(CALCULATE_DEVICE, non_blocking=True)

        # compute output
        output = model(images)

        loss = criterion(output, target)

        # measure accuracy and record loss
        acc1, acc5 = accuracy(output, target, topk=(1, 5))
        losses.update(loss.item(), images.size(0))
        top1.update(acc1[0], images.size(0))
        top5.update(acc5[0], images.size(0))

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % LOG_STEP == 0:
            progress.display(i)

        if i == TRAIN_STEP:
            break


def validate(model, criterion):
    batch_time = AverageMeter('Time', ':6.3f')
    losses = AverageMeter('Loss', ':.4e')
    top1 = AverageMeter('Acc@1', ':6.2f')
    top5 = AverageMeter('Acc@5', ':6.2f')
    progress = ProgressMeter(
        1,
        [batch_time, losses, top1, top5],
        prefix='Test: ')

    def fake_val_data(num):
        while num < 5:
            num += 1
            yield (torch.randn([128, 3, 224, 224]).npu() + torch.randint(-2, 2, [128, 3, 224, 224]).npu()).cpu(), \
                    torch.randint(1, 1000, [128])

    # switch to evaluate mode
    model.eval()

    with torch.no_grad():
        end = time.time()
        for i, (images, target) in enumerate(fake_val_data(0)):
            if 'npu' in CALCULATE_DEVICE:
                target = target.to(torch.int32)
            images, target = images.to(CALCULATE_DEVICE, non_blocking=True),\
                target.to(CALCULATE_DEVICE, non_blocking=True)
            # compute output
            output = model(images)
            loss = criterion(output, target)

            # measure accuracy and record loss
            acc1, acc5 = accuracy(output, target, topk=(1, 5))
            losses.update(loss.item(), images.size(0))
            top1.update(acc1[0], images.size(0))
            top5.update(acc5[0], images.size(0))

            # measure elapsed time
            batch_time.update(time.time() - end)
            end = time.time()

            if i % LOG_STEP == 0:
                progress.display(i)
            break
        print(' * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'
              .format(top1=top1, top5=top5))

    return top1.avg


def save_checkpoint(state, is_best, filename='checkpoint.pth.tar'):
    torch.save(state, filename)
    if is_best:
        shutil.copyfile(filename, 'model_best.pth.tar')


class AverageMeter(object):
    """Computes and stores the average and current value"""

    def __init__(self, name, fmt=':f'):
        self.name = name
        self.fmt = fmt
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

    def __str__(self):
        fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
        return fmtstr.format(**self.__dict__)


class ProgressMeter(object):
    def __init__(self, num_batches, meters, prefix=""):
        self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
        self.meters = meters
        self.prefix = prefix

    def display(self, batch):
        entries = [self.prefix + self.batch_fmtstr.format(batch)]
        entries += [str(meter) for meter in self.meters]
        print('\t'.join(entries))

    def _get_batch_fmtstr(self, num_batches):
        num_digits = len(str(num_batches // 1))
        fmt = '{:' + str(num_digits) + 'd}'
        return '[' + fmt + '/' + fmt.format(num_batches) + ']'


def adjust_learning_rate(optimizer, epoch, args):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    lr = args.lr * (0.1 ** (epoch // 30))
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr


def accuracy(output, target, topk=(1,)):
    """Computes the accuracy over the k top predictions for the specified values of k"""
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


class TestResnet(TestCase):
    def test_resnet(self):
        if models is None:
            self.skipTest(
                "torchvision is not available or not compatible with current PyTorch version"
            )
        if 'npu' in CALCULATE_DEVICE:
            torch.npu.set_device(CALCULATE_DEVICE)
        run_resnet()


if __name__ == '__main__':
    run_tests()