import numpy as np
import os.path as osp
import torch_fidelity
from PIL import Image
from tqdm import tqdm
import pickle as pkl
import os, hashlib, pdb
from pathlib import Path
from torch import Tensor
import torch, torchvision
from einops import rearrange
from omegaconf import OmegaConf
import torch.distributed as dist
from typing import List, Optional
from torchvision import transforms
from io import BytesIO as Bytes2Data
from smart_open import open
from .misc import is_main_process, get_rank
import importlib, datetime, requests, time, shutil
from collections import defaultdict, deque, OrderedDict
from dotwiz import DotWiz

URL_MAP = {
    "vgg_lpips": "https://heibox.uni-heidelberg.de/f/607503859c864bc1b30b/?dl=1"
}

CKPT_MAP = {
    "vgg_lpips": "vgg.pth"
}

MD5_MAP = {
    "vgg_lpips": "d507d7349b931f0638a25a48a722f98a"
}

def disabled_train(self, mode=True):
    """Overwrite model.train with this function to make sure train/eval mode
    does not change anymore."""
    return self
    
def customized_collate_fn(batch):

    collate_fn = {}
    if len(batch) < 2:
        for key, value in batch[0].items():
            collate_fn[key] = [value]
    else:

        for i, dd in enumerate(batch):
            if i < 1:
                for key, value in dd.items():
                    collate_fn[key] = [value]
            else:
                for key, value in dd.items():
                    collate_fn[key].append(value)
    
    return collate_fn


def trivial_batch_collator(batch):
    """
    A batch collator that does nothing.
    """
    return batch

class NestedTensor(object):
    def __init__(self, tensors, mask: Optional[Tensor]):
        self.tensors = tensors
        self.mask = mask

    def to(self, device):
        # type: (Device) -> NestedTensor # noqa
        cast_tensor = self.tensors.to(device)
        mask = self.mask
        if mask is not None:
            assert mask is not None
            cast_mask = mask.to(device)
        else:
            cast_mask = None
        return NestedTensor(cast_tensor, cast_mask)

    def decompose(self):
        return self.tensors, self.mask

    def __repr__(self):
        return str(self.tensors)


def _max_by_axis(the_list):
    # type: (List[List[int]]) -> List[int]
    maxes = the_list[0]
    for sublist in the_list[1:]:
        for index, item in enumerate(sublist):
            maxes[index] = max(maxes[index], item)
    return maxes


def nested_tensor_from_tensor_list(tensor_list: List[Tensor]):
    # TODO make this more general
    if tensor_list[0].ndim == 3:
        if torchvision._is_tracing():
            # nested_tensor_from_tensor_list() does not export well to ONNX
            # call _onnx_nested_tensor_from_tensor_list() instead
            return _onnx_nested_tensor_from_tensor_list(tensor_list)

        # TODO make it support different-sized images
        max_size = _max_by_axis([list(img.shape) for img in tensor_list])
        # min_size = tuple(min(s) for s in zip(*[img.shape for img in tensor_list]))
        batch_shape = [len(tensor_list)] + max_size
        b, c, h, w = batch_shape
        dtype = tensor_list[0].dtype
        device = tensor_list[0].device
        tensor = torch.zeros(batch_shape, dtype=dtype, device=device)
        mask = torch.ones((b, h, w), dtype=torch.bool, device=device)
        for img, pad_img, m in zip(tensor_list, tensor, mask):
            pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
            m[: img.shape[1], : img.shape[2]] = False
    else:
        raise ValueError("not supported")
    return NestedTensor(tensor, mask)


# _onnx_nested_tensor_from_tensor_list() is an implementation of
# nested_tensor_from_tensor_list() that is supported by ONNX tracing.
@torch.jit.unused
def _onnx_nested_tensor_from_tensor_list(tensor_list: List[Tensor]) -> NestedTensor:
    max_size = []
    for i in range(tensor_list[0].dim()):
        max_size_i = torch.max(
            torch.stack([img.shape[i] for img in tensor_list]).to(torch.float32)
        ).to(torch.int64)
        max_size.append(max_size_i)
    max_size = tuple(max_size)

    # work around for
    # pad_img[: img.shape[0], : img.shape[1], : img.shape[2]].copy_(img)
    # m[: img.shape[1], :img.shape[2]] = False
    # which is not yet supported in onnx
    padded_imgs = []
    padded_masks = []
    for img in tensor_list:
        padding = [(s1 - s2) for s1, s2 in zip(max_size, tuple(img.shape))]
        padded_img = torch.nn.functional.pad(img, (0, padding[2], 0, padding[1], 0, padding[0]))
        padded_imgs.append(padded_img)

        m = torch.zeros_like(img[0], dtype=torch.int, device=img.device)
        padded_mask = torch.nn.functional.pad(m, (0, padding[2], 0, padding[1]), "constant", 1)
        padded_masks.append(padded_mask.to(torch.bool))

    tensor = torch.stack(padded_imgs)
    mask = torch.stack(padded_masks)

    return NestedTensor(tensor, mask=mask)


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


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=20, 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):
        """
        Warning: does not synchronize the deque!
        """
        if not is_dist_avail_and_initialized():
            return
        t = torch.tensor([self.count, self.total], dtype=torch.float64, device='cuda')
        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 v is None:
                continue
            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):
        for meter in self.meters.values():
            meter.synchronize_between_processes()

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

    def log_every(self, iterable, print_freq, 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'
        log_msg = [
            header,
            '[{0' + space_fmt + '}/{1}]',
            'eta: {eta}',
            '{meters}',
            'time: {time}',
            'data: {data}'
        ]
        if torch.cuda.is_available():
            log_msg.append('max mem: {memory:.0f}')
        log_msg = self.delimiter.join(log_msg)
        MB = 1024.0 * 1024.0
        for obj in iterable:
            data_time.update(time.time() - end)
            yield obj
            iter_time.update(time.time() - end)
            if i % print_freq == 0 or i == len(iterable) - 1:
                eta_seconds = iter_time.global_avg * (len(iterable) - i)
                eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
                if torch.cuda.is_available():
                    print(log_msg.format(
                        i, len(iterable), eta=eta_string,
                        meters=str(self),
                        time=str(iter_time), data=str(data_time),
                        memory=torch.cuda.max_memory_allocated() / MB))
                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: {} ({:.4f} s / it)'.format(
            header, total_time_str, total_time / len(iterable)))


def all_reduce_mean(x):
    world_size = dist.get_world_size()
    if world_size > 1:
        x_reduce = torch.tensor(x).cuda()
        dist.all_reduce(x_reduce)
        x_reduce /= world_size
        return x_reduce.item()
    else:
        return x


class NativeScaler:
    state_dict_key = "amp_scaler"

    def __init__(self):
        self._scaler = torch.cuda.amp.GradScaler()

    def __call__(self, loss, optimizer, clip_grad=3., parameters=None, create_graph=False, update_grad=True):
        self._scaler.scale(loss).backward(create_graph=create_graph)
        if update_grad:
            if clip_grad is not None:
                assert parameters is not None
                self._scaler.unscale_(optimizer)  # unscale the gradients of optimizer's assigned params in-place
                norm = torch.nn.utils.clip_grad_norm_(parameters, clip_grad)
            else:
                self._scaler.unscale_(optimizer)
                norm = get_grad_norm_(parameters)
            self._scaler.step(optimizer)
            self._scaler.update()
        else:
            norm = None
        return norm

    def state_dict(self):
        return self._scaler.state_dict()

    def load_state_dict(self, state_dict):
        self._scaler.load_state_dict(state_dict)


def get_grad_norm_(parameters, norm_type: float = 2.0) -> torch.Tensor:
    if isinstance(parameters, torch.Tensor):
        parameters = [parameters]
    parameters = [p for p in parameters if p.grad is not None and p.requires_grad]
    norm_type = float(norm_type)
    if len(parameters) == 0:
        return torch.tensor(0.)
    device = parameters[0].grad.device
    total_norm = torch.norm(torch.stack([torch.norm(p.grad.detach(), norm_type).to(device) for p in parameters]),
                            norm_type)
    return total_norm


def get_obj_from_str(string, reload=False):
    module, cls = string.rsplit(".", 1)
    if reload:
        module_imp = importlib.import_module(module)
        importlib.reload(module_imp)
    return getattr(importlib.import_module(module, package=None), cls)


def instantiate_from_config(config):
    if not "target" in config:
        raise KeyError("Expected key `target` to instantiate.")
    return get_obj_from_str(config["target"])(**config.get("params", dict()))


def save_on_master(*args, **kwargs):
    if dist.get_rank() == 0:
        torch.save(*args, **kwargs)


def save_model(args, epoch, model, model_without_ddp, optimizer_g, optimizer_d, loss_scaler):
    output_dir = Path(args.output_dir)
    epoch_name = str(epoch)
    if loss_scaler is not None:
        checkpoint_paths = [output_dir / ('checkpoint-%s.pth' % epoch_name)]
        for checkpoint_path in checkpoint_paths:
            to_save = {
                'model': model_without_ddp.state_dict(),
                'optimizer_g': optimizer_g.state_dict(),
                'optimizer_d': optimizer_d.state_dict(),
                'epoch': epoch,
                'scaler': loss_scaler.state_dict(),
                'args': args,
            }

            save_on_master(to_save, checkpoint_path)
    else:
        client_state = {'epoch': epoch}
        model.save_checkpoint(save_dir=args.output_dir, tag="checkpoint-%s" % epoch_name, client_state=client_state)


def load_model(args, model_without_ddp, optimizer_g, optimizer_d, loss_scaler):
    if args.resume:
        if args.resume.startswith('https'):
            checkpoint = torch.hub.load_state_dict_from_url(
                args.resume, map_location='cpu', check_hash=True)
        else:
            checkpoint = torch.load(args.resume, map_location='cpu')
        model_without_ddp.load_state_dict(checkpoint['model'])
        print("Resume checkpoint %s" % args.resume)
        if 'optimizer_g' in checkpoint and 'epoch' in checkpoint and not (hasattr(args, 'eval') and args.eval):
            optimizer_g.load_state_dict(checkpoint['optimizer_g'])
            optimizer_d.load_state_dict(checkpoint['optimizer_d'])
            args.start_epoch = checkpoint['epoch'] + 1
            if 'scaler' in checkpoint:
                loss_scaler.load_state_dict(checkpoint['scaler'])
            print("With optim & sched!")


def download(url, local_path, chunk_size=1024):
    os.makedirs(os.path.split(local_path)[0], exist_ok=True)
    with requests.get(url, stream=True) as r:
        total_size = int(r.headers.get("content-length", 0))
        with tqdm(total=total_size, unit="B", unit_scale=True) as pbar:
            with open(local_path, "wb") as f:
                for data in r.iter_content(chunk_size=chunk_size):
                    if data:
                        f.write(data)
                        pbar.update(chunk_size)


def md5_hash(path):
    with open(path, "rb") as f:
        content = f.read()
    return hashlib.md5(content).hexdigest()


def get_ckpt_path(name, root, check=False):
    assert name in URL_MAP
    path = os.path.join(root, CKPT_MAP[name])
    if not os.path.exists(path) or (check and not md5_hash(path) == MD5_MAP[name]):
        print("Downloading {} model from {} to {}".format(name, URL_MAP[name], path))
        download(URL_MAP[name], path)
        md5 = md5_hash(path)
        assert md5 == MD5_MAP[name], md5
    return path


class KeyNotFoundError(Exception):
    def __init__(self, cause, keys=None, visited=None):
        self.cause = cause
        self.keys = keys
        self.visited = visited
        messages = list()
        if keys is not None:
            messages.append("Key not found: {}".format(keys))
        if visited is not None:
            messages.append("Visited: {}".format(visited))
        messages.append("Cause:\n{}".format(cause))
        message = "\n".join(messages)
        super().__init__(message)


def retrieve(
        list_or_dict, key, splitval="/", default=None, expand=True, pass_success=False
):
    """Given a nested list or dict return the desired value at key expanding
    callable nodes if necessary and :attr:`expand` is ``True``. The expansion
    is done in-place.

    Parameters
    ----------
        list_or_dict : list or dict
            Possibly nested list or dictionary.
        key : str
            key/to/value, path like string describing all keys necessary to
            consider to get to the desired value. List indices can also be
            passed here.
        splitval : str
            String that defines the delimiter between keys of the
            different depth levels in `key`.
        default : obj
            Value returned if :attr:`key` is not found.
        expand : bool
            Whether to expand callable nodes on the path or not.

    Returns
    -------
        The desired value or if :attr:`default` is not ``None`` and the
        :attr:`key` is not found returns ``default``.

    Raises
    ------
        Exception if ``key`` not in ``list_or_dict`` and :attr:`default` is
        ``None``.
    """

    keys = key.split(splitval)

    success = True
    try:
        visited = []
        parent = None
        last_key = None
        for key in keys:
            if callable(list_or_dict):
                if not expand:
                    raise KeyNotFoundError(
                        ValueError(
                            "Trying to get past callable node with expand=False."
                        ),
                        keys=keys,
                        visited=visited,
                    )
                list_or_dict = list_or_dict()
                parent[last_key] = list_or_dict

            last_key = key
            parent = list_or_dict

            try:
                if isinstance(list_or_dict, dict):
                    list_or_dict = list_or_dict[key]
                else:
                    list_or_dict = list_or_dict[int(key)]
            except (KeyError, IndexError, ValueError) as e:
                raise KeyNotFoundError(e, keys=keys, visited=visited)

            visited += [key]
        # final expansion of retrieved value
        if expand and callable(list_or_dict):
            list_or_dict = list_or_dict()
            parent[last_key] = list_or_dict
    except KeyNotFoundError as e:
        if default is None:
            raise e
        else:
            list_or_dict = default
            success = False

    if not pass_success:
        return list_or_dict
    else:
        return list_or_dict, success


if __name__ == "__main__":
    config = {"keya": "a",
              "keyb": "b",
              "keyc":
                  {"cc1": 1,
                   "cc2": 2,
                   }
              }
    from omegaconf import OmegaConf

    config = OmegaConf.create(config)
    print(config)
    retrieve(config, "keya")

def instantiate_from_config(config):

    if not "target" in config:
        raise KeyError("Expected key `target` to instantiate.")
    return get_obj_from_str(config["target"])(**config.get("params", dict()))

def get_obj_from_str(string, reload=False):
    module, cls = string.rsplit(".", 1)
    if reload:
        module_imp = importlib.import_module(module)
        importlib.reload(module_imp)
    return getattr(importlib.import_module(module, package=None), cls)