# Copyright 2020 Ross Wightman
# Various utility functions

import torch
import torch.nn as nn
from functools import partial
import math
import warnings
import torch.nn.functional as F

from timesformer.models.helpers import load_pretrained
from .build import MODEL_REGISTRY
from itertools import repeat
from collections import abc as container_abcs
# from torch._six import container_abcs

DEFAULT_CROP_PCT = 0.875
IMAGENET_DEFAULT_MEAN = (0.485, 0.456, 0.406)
IMAGENET_DEFAULT_STD = (0.229, 0.224, 0.225)
IMAGENET_INCEPTION_MEAN = (0.5, 0.5, 0.5)
IMAGENET_INCEPTION_STD = (0.5, 0.5, 0.5)
IMAGENET_DPN_MEAN = (124 / 255, 117 / 255, 104 / 255)
IMAGENET_DPN_STD = tuple([1 / (.0167 * 255)] * 3)

def _no_grad_trunc_normal_(tensor, mean, std, a, b):
    def norm_cdf(x):
        # Computes standard normal cumulative distribution function
        return (1. + math.erf(x / math.sqrt(2.))) / 2.

    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
        l = norm_cdf((a - mean) / std)
        u = norm_cdf((b - mean) / std)

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

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

def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
    # type: (Tensor, float, float, float, float) -> Tensor
    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)

# From PyTorch internals
def _ntuple(n):
    def parse(x):
        if isinstance(x, container_abcs.Iterable):
            return x
        return tuple(repeat(x, n))
    return parse
to_2tuple = _ntuple(2)

# Calculate symmetric padding for a convolution
def get_padding(kernel_size: int, stride: int = 1, dilation: int = 1, **_) -> int:
    padding = ((stride - 1) + dilation * (kernel_size - 1)) // 2
    return padding

def get_padding_value(padding, kernel_size, **kwargs):
    dynamic = False
    if isinstance(padding, str):
        # for any string padding, the padding will be calculated for you, one of three ways
        padding = padding.lower()
        if padding == 'same':
            # TF compatible 'SAME' padding, has a performance and GPU memory allocation impact
            if is_static_pad(kernel_size, **kwargs):
                # static case, no extra overhead
                padding = get_padding(kernel_size, **kwargs)
            else:
                # dynamic 'SAME' padding, has runtime/GPU memory overhead
                padding = 0
                dynamic = True
        elif padding == 'valid':
            # 'VALID' padding, same as padding=0
            padding = 0
        else:
            # Default to PyTorch style 'same'-ish symmetric padding
            padding = get_padding(kernel_size, **kwargs)
    return padding, dynamic

# Calculate asymmetric TensorFlow-like 'SAME' padding for a convolution
def get_same_padding(x: int, k: int, s: int, d: int):
    return max((int(math.ceil(x // s)) - 1) * s + (k - 1) * d + 1 - x, 0)


# Can SAME padding for given args be done statically?
def is_static_pad(kernel_size: int, stride: int = 1, dilation: int = 1, **_):
    return stride == 1 and (dilation * (kernel_size - 1)) % 2 == 0


# Dynamically pad input x with 'SAME' padding for conv with specified args
#def pad_same(x, k: List[int], s: List[int], d: List[int] = (1, 1), value: float = 0):
def pad_same(x, k, s, d=(1, 1), value= 0):
    ih, iw = x.size()[-2:]
    pad_h, pad_w = get_same_padding(ih, k[0], s[0], d[0]), get_same_padding(iw, k[1], s[1], d[1])
    if pad_h > 0 or pad_w > 0:
        x = F.pad(x, [pad_w // 2, pad_w - pad_w // 2, pad_h // 2, pad_h - pad_h // 2], value=value)
    return x

def adaptive_pool_feat_mult(pool_type='avg'):
    if pool_type == 'catavgmax':
        return 2
    else:
        return 1

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

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