# Copyright (c) OpenMMLab. All rights reserved.
import functools

import torch.nn.functional as F


def reduce_loss(loss, reduction):
    """Reduce loss as specified.

    Args:
        loss (Tensor): Elementwise loss tensor.
        reduction (str): Options are "none", "mean", "sum", "flatmean" and
            "batchmean". 'none': no reduction will be applied. 'mean': the
            output will be divided by the number of elements in the output.
            'sum': the output will be summed. 'batchmean': the sum of the
            output will be divided by batchsize. 'flatmean': each sample
            will be divided by the number of element respectively and
            output will shape as [bz, ].

    Return:
        Tensor: Reduced loss tensor.
    """
    if reduction == 'batchmean':
        return loss.sum() / loss.shape[0]

    if reduction == 'flatmean':
        return loss.mean(dim=list(range(1, loss.ndim)))

    reduction_enum = F._Reduction.get_enum(reduction)
    # none: 0, elementwise_mean:1, sum: 2
    if reduction_enum == 0:
        return loss

    if reduction_enum == 1:
        return loss.mean()

    if reduction_enum == 2:
        return loss.sum()

    raise ValueError(f'reduction type {reduction} not supported')


def weight_reduce_loss(loss, weight=None, reduction='mean', avg_factor=None):
    """Apply element-wise weight and reduce loss.

    Args:
        loss (Tensor): Element-wise loss.
        weight (Tensor): Element-wise weights.
        reduction (str): Same as built-in losses of PyTorch.
        avg_factor (float): Average factor when computing the mean of losses.

    Returns:
        Tensor: Processed loss values.
    """
    # if weight is specified, apply element-wise weight
    if weight is not None:
        loss = loss * weight

    # if avg_factor is not specified, just reduce the loss
    if avg_factor is None:
        loss = reduce_loss(loss, reduction)
    else:
        # if reduction is mean, then average the loss by avg_factor
        if reduction == 'mean':
            loss = loss.sum() / avg_factor
        # if reduction is 'none', then do nothing, otherwise raise an error
        elif reduction != 'none':
            raise ValueError('avg_factor can not be used with reduction="sum"')
    return loss


def weighted_loss(loss_func):
    """Create a weighted version of a given loss function.

    To use this decorator, the loss function must have the signature like
    `loss_func(pred, target, **kwargs)`. The function only needs to compute
    element-wise loss without any reduction. This decorator will add weight
    and reduction arguments to the function. The decorated function will have
    the signature like `loss_func(pred, target, weight=None, reduction='mean',
    avg_factor=None, **kwargs)`.

    :Example:

    >>> import torch
    >>> @weighted_loss
    >>> def l1_loss(pred, target):
    >>>     return (pred - target).abs()

    >>> pred = torch.Tensor([0, 2, 3])
    >>> target = torch.Tensor([1, 1, 1])
    >>> weight = torch.Tensor([1, 0, 1])

    >>> l1_loss(pred, target)
    tensor(1.3333)
    >>> l1_loss(pred, target, weight)
    tensor(1.)
    >>> l1_loss(pred, target, reduction='none')
    tensor([1., 1., 2.])
    >>> l1_loss(pred, target, weight, avg_factor=2)
    tensor(1.5000)
    """

    @functools.wraps(loss_func)
    def wrapper(*args,
                weight=None,
                reduction='mean',
                avg_factor=None,
                **kwargs):
        # get element-wise loss
        loss = loss_func(*args, **kwargs)
        loss = weight_reduce_loss(loss, weight, reduction, avg_factor)
        return loss

    return wrapper