import datetime
import os
import time

import torch
import torch.utils.data
from torch import nn
from torchvision import transforms
from resnet import resnet152
import utils

def train_one_epoch(model, criterion, optimizer, data_loader, device, epoch, print_freq):
    model.train()
    metric_logger = utils.MetricLogger(delimiter="  ")
    metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value}'))
    metric_logger.add_meter('img/s', utils.SmoothedValue(window_size=10, fmt='{value}'))

    header = 'Epoch: [{}]'.format(epoch)
    for image, antibody, target in metric_logger.log_every(data_loader, print_freq, header):
        start_time = time.time()
        image, antibody, target = image.to(device), antibody.to(device), target.to(device)
        output = model(image, antibody)
        loss = criterion(output, target)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        acc1, acc5 = utils.accuracy(output, target, topk=(1, 2))
        batch_size = image.shape[0]
        metric_logger.update(loss=loss.item(), lr=optimizer.param_groups[0]["lr"])
        metric_logger.meters['acc1'].update(acc1.item(), n=batch_size)
        metric_logger.meters['acc2'].update(acc5.item(), n=batch_size)
        metric_logger.meters['img/s'].update(batch_size / (time.time() - start_time))


def evaluate(model, criterion, data_loader, device, print_freq=100):
    model.eval()
    metric_logger = utils.MetricLogger(delimiter="  ")
    header = 'Test:'
    with torch.no_grad():
        for image, antibody, target in metric_logger.log_every(data_loader, print_freq, header):
            image = image.to(device, non_blocking=True)
            antibody = antibody.to(device, non_blocking=True)
            target = target.to(device, non_blocking=True)
            output = model(image, antibody)
            loss = criterion(output, target)

            acc1, acc5 = utils.accuracy(output, target, topk=(1, 2))
            # FIXME need to take into account that the datasets
            # could have been padded in distributed setup
            batch_size = image.shape[0]
            metric_logger.update(loss=loss.item())
            metric_logger.meters['acc1'].update(acc1.item(), n=batch_size)
            metric_logger.meters['acc2'].update(acc5.item(), n=batch_size)
    # gather the stats from all processes
    metric_logger.synchronize_between_processes()

    print(' * Acc@1 {top1.global_avg:.3f} Acc@2 {top5.global_avg:.3f}'
          .format(top1=metric_logger.acc1, top5=metric_logger.acc2))
    return metric_logger.acc1.global_avg


def _get_cache_path(filepath):
    import hashlib
    h = hashlib.sha1(filepath.encode()).hexdigest()
    cache_path = os.path.join("~", ".torch", "vision", "datasets", "imagefolder", h[:10] + ".pt")
    cache_path = os.path.expanduser(cache_path)
    return cache_path


def load_data(traindir, valdir, antibody_train, antibody_val, cache_dataset, distributed):
    # Data loading code
    print("Loading data")
    normalize = transforms.Normalize(mean=[0.168, 0.174, 0.182],
                                     std =[0.159, 0.160, 0.162])
    
    expression_tfs = transforms.Compose([nn.Dropout(0.3)])
    
    print("Loading data")
    st = time.time()
  
    dataset = utils.HTDataset(
            traindir, antibody_train,
            transforms.Compose([
                transforms.RandomResizedCrop(224),
                transforms.RandomHorizontalFlip(),
                transforms.RandomRotation(degrees=180),
                transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.0),
                transforms.ToTensor(),
                normalize,
            ]), expression_tfs)
    
    dataset_test = utils.HTDataset(
            valdir, antibody_val,
            transforms.Compose([
                transforms.Resize(256),
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                normalize,
            ]), None)
        
    print("Took", time.time() - st)

    print("Creating data loaders")
    if distributed:
        train_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
        test_sampler = torch.utils.data.distributed.DistributedSampler(dataset_test)
    else:
        train_sampler = torch.utils.data.RandomSampler(dataset)
        test_sampler = torch.utils.data.SequentialSampler(dataset_test)

    return dataset, dataset_test, train_sampler, test_sampler


def main(args):

    if args.output_dir:
        utils.mkdir(args.output_dir)

    utils.init_distributed_mode(args)
    print(args)

    device = torch.device(args.device)
    torch.backends.cudnn.benchmark = True

    train_dir = args.train_file
    val_dir = args.val_file
    dataset, dataset_test, train_sampler, test_sampler = load_data(train_dir, val_dir,
                                                                   args.antibodytrn, args.antibodyval,
                                                                   args.cache_dataset, args.distributed)
    data_loader = torch.utils.data.DataLoader(
        dataset, batch_size=args.batch_size,
        sampler=train_sampler, num_workers=args.workers, pin_memory=True)

    data_loader_test = torch.utils.data.DataLoader(
        dataset_test, batch_size=args.batch_size,
        sampler=test_sampler, num_workers=args.workers, pin_memory=True)

    print("Creating model")
    model = resnet152(num_classes=2, antibody_nums=6) # 6 antibodies
    image_checkpoint = "../hashimoto_thyroiditis/model_79.pth"
    flag = os.path.exists(image_checkpoint)

    if flag:
        checkpoint = torch.load(image_checkpoint, map_location='cpu')
        msg = model.load_state_dict(checkpoint['model'], strict=False)
        print(msg)
    
        print("Parameters to be updated:")
        parameters_to_be_updated = ['fc.weight', 'fc.bias'] + msg.missing_keys
        print(parameters_to_be_updated)
    
        for name, param in model.named_parameters():
            if name not in parameters_to_be_updated:
                param.requires_grad = False
        
    model.to(device)
    if args.distributed and args.sync_bn:
        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model)

    if flag:
        parameters = list(filter(lambda p: p.requires_grad, model.parameters()))
        assert len(parameters) == len(parameters_to_be_updated)
    else:
        parameters = model.parameters()
 
    criterion = nn.CrossEntropyLoss()

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

    lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.lr_step_size, gamma=args.lr_gamma)

    model_without_ddp = model
    if args.distributed:
        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
        model_without_ddp = model.module

    if args.resume:
        checkpoint = torch.load(args.resume, map_location='cpu')
        model_without_ddp.load_state_dict(checkpoint['model'])
        optimizer.load_state_dict(checkpoint['optimizer'])
        lr_scheduler.load_state_dict(checkpoint['lr_scheduler'])
        args.start_epoch = checkpoint['epoch'] + 1

    if args.test_only:
        evaluate(model, criterion, data_loader_test, device=device)
        return

    print("Start training")
    start_time = time.time()
    for epoch in range(args.start_epoch, args.epochs):
        if args.distributed:
            train_sampler.set_epoch(epoch)
        train_one_epoch(model, criterion, optimizer, data_loader, device, epoch, args.print_freq)
        lr_scheduler.step()
        evaluate(model, criterion, data_loader_test, device=device)
        if args.output_dir:
            checkpoint = {
                'model': model_without_ddp.state_dict(),
                'optimizer': optimizer.state_dict(),
                'lr_scheduler': lr_scheduler.state_dict(),
                'epoch': epoch,
                'args': args}
            utils.save_on_master(
                checkpoint,
                os.path.join(args.output_dir, 'model_{}.pth'.format(epoch)))
            utils.save_on_master(
                checkpoint,
                os.path.join(args.output_dir, 'checkpoint.pth'))

    total_time = time.time() - start_time
    total_time_str = str(datetime.timedelta(seconds=int(total_time)))
    print('Training time {}'.format(total_time_str))


def parse_args():
    import argparse
    parser = argparse.ArgumentParser(description='PyTorch Classification Training')

    parser.add_argument('--train-file', help='training set of image file')
    parser.add_argument('--val-file', help='validation set of image file')
    parser.add_argument('--antibodytrn', help='training set of antibody')
    parser.add_argument('--antibodyval', help='validation set of antibody')
    parser.add_argument('--num-classes', help='number of classes for the objective task', type=int)
    
    parser.add_argument('--device', default='cuda', help='device')
    parser.add_argument('-b', '--batch-size', default=32, type=int)
    parser.add_argument('--epochs', default=90, type=int, metavar='N',
                        help='number of total epochs to run')
    parser.add_argument('-j', '--workers', default=16, type=int, metavar='N',
                        help='number of data loading workers (default: 16)')
    parser.add_argument('--lr', default=0.1, type=float, help='initial learning rate')
    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('--lr-step-size', default=30, type=int, help='decrease lr every step-size epochs')
    parser.add_argument('--lr-gamma', default=0.1, type=float, help='decrease lr by a factor of lr-gamma')
    parser.add_argument('--print-freq', default=10, type=int, help='print frequency')
    parser.add_argument('--output-dir', default='.', help='path where to save')
    parser.add_argument('--resume', default='', help='resume from checkpoint')
    parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
                        help='start epoch')
    parser.add_argument(
        "--cache-dataset",
        dest="cache_dataset",
        help="Cache the datasets for quicker initialization. It also serializes the transforms",
        action="store_true",
    )
    parser.add_argument(
        "--sync-bn",
        dest="sync_bn",
        help="Use sync batch norm",
        action="store_true",
    )
    parser.add_argument(
        "--test-only",
        dest="test_only",
        help="Only test the model",
        action="store_true",
    )
    parser.add_argument(
        "--pretrained",
        dest="pretrained",
        help="Use pre-trained models from the modelzoo",
        action="store_true",
    )

    # distributed training parameters
    parser.add_argument('--world-size', default=1, type=int,
                        help='number of distributed processes')
    parser.add_argument('--dist-url', default='env://', help='url used to set up distributed training')

    args = parser.parse_args()

    return args


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