import math
import warnings
from itertools import repeat

import torch
from torch import nn
from torch._six import container_abcs


def drop_path(x, drop_prob: float = 0.0, training: bool = False):
    """
    Drop paths (Stochastic Depth) per sample (when applied in main
    path of residual blocks). This is the same as the DropConnect impl
    I created for EfficientNet, etc networks, however, the original name
    is misleading as 'Drop Connect' is a different form of dropout in a
    separate paper... See discussion:
    https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ...
    I've opted for changing the layer and argument names to 'drop path'
    rather than mix DropConnect as a layer name and use 'survival rate'
    as the argument.
    """
    if drop_prob == 0.0 or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (
        x.ndim - 1
    )  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    """
    Drop paths (Stochastic Depth) per sample
    (when applied in main path of residual blocks).
    """

    def __init__(self, drop_prob: float = None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)


# From PyTorch internals
def _ntuple(n: int):
    def parse(x):
        if isinstance(x, container_abcs.Iterable):
            return x
        return tuple(repeat(x, n))

    return parse


to_1tuple = _ntuple(1)
to_2tuple = _ntuple(2)
to_3tuple = _ntuple(3)
to_4tuple = _ntuple(4)


def _no_grad_trunc_normal_(
    tensor: torch.tensor, mean: float, std: float, a: float, b: float
):
    # Cut & paste from PyTorch official master
    # until it's in a few official releases - RW
    # Method based on:
    # https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf
    def norm_cdf(x):
        # Computes standard normal cumulative distribution function
        return (1.0 + math.erf(x / math.sqrt(2.0))) / 2.0

    if (mean < a - 2 * std) or (mean > b + 2 * std):
        warnings.warn(
            "mean is more than 2 std from [a, b] in nn.init.trunc_normal_. "
            "The distribution of values may be incorrect.",
            stacklevel=2,
        )

    with torch.no_grad():
        # Values are generated by using a truncated uniform distribution and
        # then using the inverse CDF for the normal distribution.
        # Get upper and lower cdf values
        lower = norm_cdf((a - mean) / std)
        upper = norm_cdf((b - mean) / std)

        # Uniformly fill tensor with values from [l, u], then translate to
        # [2l-1, 2u-1].
        tensor.uniform_(2 * lower - 1, 2 * upper - 1)

        # Use inverse cdf transform for normal distribution to get truncated
        # standard normal
        tensor.erfinv_()

        # Transform to proper mean, std
        tensor.mul_(std * math.sqrt(2.0))
        tensor.add_(mean)

        # Clamp to ensure it's in the proper range
        tensor.clamp_(min=a, max=b)
        return tensor


def trunc_normal_(
    tensor: torch.tensor,
    mean: float = 0.0,
    std: float = 1.0,
    a: float = -2.0,
    b: float = 2.0,
):
    r"""Fills the input Tensor with values drawn from a truncated
    normal distribution. The values are effectively drawn from the
    normal distribution :math:`\mathcal{N}(\text{mean}, \text{std}^2)`
    with values outside :math:`[a, b]` redrawn until they are within
    the bounds. The method used for generating the random values works
    best when :math:`a \leq \text{mean} \leq b`.
    Args:
        tensor: an n-dimensional `torch.Tensor`
        mean: the mean of the normal distribution
        std: the standard deviation of the normal distribution
        a: the minimum cutoff value
        b: the maximum cutoff value
    Examples:
        >>> w = torch.empty(3, 5)
        >>> nn.init.trunc_normal_(w)
    """
    return _no_grad_trunc_normal_(tensor, mean, std, a, b)