# Copyright 2021 Huawei Technologies Co., Ltd
#
# 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.
# ============================================================================
from collections import defaultdict, deque
import datetime
import time
import torch
import torch.distributed as dist

import errno
import os

import numpy as np #RDN


class AverageMeter(object):
    def __init__(self,start_count_index=0):
        self.start_count_index = start_count_index
        self.reset()

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


    def update(self, val, n=1):
        if self.count == 0:
            self.N = n

        self.val = val
        self.count += n
        if self.count > (self.start_count_index * self.N):
            self.sum += val * n
            self.avg = self.sum / (self.count - self.start_count_index * self.N)
            
class SmoothedValue(object):
    """Track a series of values and provide access to smoothed values over a
    window or the global series average.
    """

    def __init__(self, window_size=50, fmt=None):
        if fmt is None:
            fmt = "{median:.4f} ({global_avg:.4f})"
        self.deque = deque(maxlen=window_size)
        self.total = 0.0
        self.count = 0
        self.fmt = fmt

    def update(self, value, n=1):
        self.deque.append(value)
        self.count += n
        self.total += value * n

    def synchronize_between_processes(self, npu_device):
        """
        Warning: does not synchronize the deque!
        """
        if not is_dist_avail_and_initialized():
            return
        t = torch.tensor([self.count, self.total], dtype=torch.float32, device=npu_device)
        dist.barrier()
        dist.all_reduce(t)
        t = t.tolist()
        self.count = int(t[0])
        self.total = t[1]

    @property
    def median(self):
        d = torch.tensor(list(self.deque))
        return d.median().item()

    @property
    def avg(self):
        d = torch.tensor(list(self.deque), dtype=torch.float32)
        return d.mean().item()

    @property
    def global_avg(self):
        return self.total / self.count

    @property
    def max(self):
        return max(self.deque)

    @property
    def value(self):
        return self.deque[-1]

    def __str__(self):
        return self.fmt.format(
            median=self.median,
            avg=self.avg,
            global_avg=self.global_avg,
            max=self.max,
            value=self.value)


class MetricLogger(object):
    def __init__(self, delimiter="\t"):
        self.meters = defaultdict(SmoothedValue)
        self.delimiter = delimiter

    def update(self, **kwargs):
        for k, v in kwargs.items():
            if isinstance(v, torch.Tensor):
                v = v.item()
            assert isinstance(v, (float, int))
            self.meters[k].update(v)

    def __getattr__(self, attr):
        if attr in self.meters:
            return self.meters[attr]
        if attr in self.__dict__:
            return self.__dict__[attr]
        raise AttributeError("'{}' object has no attribute '{}'".format(
            type(self).__name__, attr))

    def __str__(self):
        loss_str = []
        for name, meter in self.meters.items():
            loss_str.append(
                "{}: {}".format(name, str(meter))
            )
        return self.delimiter.join(loss_str)

    def synchronize_between_processes(self, device):
        for meter in self.meters.values():
            meter.synchronize_between_processes(device)

    def add_meter(self, name, meter):
        self.meters[name] = meter

    def log_every(self, iterable, args, header=None):
        i = 0
        if not header:
            header = ''
        start_time = time.time()
        end = time.time()
        iter_time = SmoothedValue(fmt='{avg:.4f}')
        data_time = SmoothedValue(fmt='{avg:.4f}')
        space_fmt = ':' + str(len(str(len(iterable)))) + 'd'
        if torch.npu.is_available():
            log_msg = self.delimiter.join([
                header,
                '[{0' + space_fmt + '}/{1}]',
                'eta: {eta}',
                '{meters}',
                'time: {time}',
                'data: {data}',
                'max mem: {memory:.0f}'
            ])
        else:
            log_msg = self.delimiter.join([
                header,
                '[{0' + space_fmt + '}/{1}]',
                'eta: {eta}',
                '{meters}',
                'time: {time}',
                'data: {data}'
            ])
        MB = 1024.0 * 1024.0
        for obj in iterable:
            data_time.update(time.time() - end)
            yield obj
            iter_time.update(time.time() - end)
            if args.is_master_node and i % args.print_freq == 0:
                eta_seconds = iter_time.global_avg * (len(iterable) - i)
                eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
                if torch.npu.is_available():
               # if torch.cuda.is_available():   # for RDN in GPU
                    print(log_msg.format(
                        i, len(iterable), eta=eta_string,
                        meters=str(self),
                        time=str(iter_time), data=str(data_time),
                        memory=0))
                else:
                    print(log_msg.format(
                        i, len(iterable), eta=eta_string,
                        meters=str(self),
                        time=str(iter_time), data=str(data_time)))
            i += 1
            end = time.time()
        total_time = time.time() - start_time
        total_time_str = str(datetime.timedelta(seconds=int(total_time)))
        print('{} Total time: {}'.format(header, total_time_str))


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[None])

        res = []
        for k in topk:
            correct_k = correct[:k].flatten().sum(dtype=torch.float32)
            res.append(correct_k * (100.0 / batch_size))
        return res


def mkdir(path):
    try:
        os.makedirs(path)
    except OSError as e:
        if e.errno != errno.EEXIST:
            raise


def setup_for_distributed(is_master):
    """
    This function disables printing when not in master process
    """
    import builtins as __builtin__
    builtin_print = __builtin__.print

    def print(*args, **kwargs):
        force = kwargs.pop('force', False)
        if is_master or force:
            builtin_print(*args, **kwargs)

    __builtin__.print = print


def is_dist_avail_and_initialized():
    if not dist.is_available():
        return False
    if not dist.is_initialized():
        return False
    return True


def get_world_size():
    if not is_dist_avail_and_initialized():
        return 1
    return dist.get_world_size()


def get_rank():
    if not is_dist_avail_and_initialized():
        return 0
    return dist.get_rank()


def is_main_process():
    return get_rank() == 0


def save_on_master(*args, **kwargs):
    torch.save(*args, **kwargs)


def init_distributed_mode(args):
    if 'RANK_SIZE' in os.environ and 'RANK_ID' in os.environ:
        args.rank_size = int(os.environ['RANK_SIZE'])
        args.rank_id = int(os.environ['RANK_ID'])
        args.rank = args.dist_rank * args.rank_size + args.rank_id
        args.world_size = args.world_size * args.rank_size
        args.device_id = args.rank_id
        args.batch_size = int(args.batch_size / args.rank_size)
        args.workers = int((args.workers + args.rank_size - 1) / args.rank_size)
    else:
        raise RuntimeError("init_distributed_mode failed.")

    torch.distributed.init_process_group(backend='hccl', init_method='env://',
                                          world_size=args.world_size, rank=args.rank)
                                       

#for RDN 
def convert_rgb_to_y(img, dim_order='hwc'):
    if dim_order == 'hwc':
        return 16. + (64.738 * img[..., 0] + 129.057 * img[..., 1] + 25.064 * img[..., 2]) / 256.
    else:
        return 16. + (64.738 * img[0] + 129.057 * img[1] + 25.064 * img[2]) / 256.


def denormalize(img):
    img = img.mul(255.0).clamp(0.0, 255.0)
    return img


def preprocess(img, device):
    img = np.array(img).astype(np.float32)
    ycbcr = convert_rgb_to_ycbcr(img)
    x = ycbcr[..., 0]
    x /= 255.
    x = torch.from_numpy(x).to(device)
    x = x.unsqueeze(0).unsqueeze(0)
    return x, ycbcr



def calc_psnr(img1,img2,scale,device,max=255.0):
    img1 = convert_rgb_to_y(denormalize(img1.squeeze(0)), dim_order='chw')
    img2 = convert_rgb_to_y(denormalize(img2.squeeze(0)), dim_order='chw')
    img1 = img1[scale:-scale, scale:-scale]
    img2 = img2[scale:-scale, scale:-scale]
    psnr =10. * ((max ** 2) / ((img1 - img2) ** 2).mean()).log10()
    return psnr