# Implementation modified from torchvision:
# https://github.com/pytorch/vision/blob/main/torchvision/ops/stochastic_depth.py
#
# License:
# BSD 3-Clause License
#
# Copyright (c) Soumith Chintala 2016,
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
#   list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
#   this list of conditions and the following disclaimer in the documentation
#   and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

import torch
import torch.fx
from torch import nn, Tensor


def stochastic_depth(
    input: Tensor, p: float, mode: str, training: bool = True
) -> Tensor:
    """
    Implements the Stochastic Depth from `"Deep Networks with Stochastic Depth"
    <https://arxiv.org/abs/1603.09382>`_ used for randomly dropping residual
    branches of residual architectures.

    Args:
        input (Tensor[N, ...]): The input tensor or arbitrary dimensions with the first one
                    being its batch i.e. a batch with ``N`` rows.
        p (float): probability of the input to be zeroed.
        mode (str): ``"batch"`` or ``"row"``.
                    ``"batch"`` randomly zeroes the entire input, ``"row"`` zeroes
                    randomly selected rows from the batch.
        training: apply stochastic depth if is ``True``. Default: ``True``

    Returns:
        Tensor[N, ...]: The randomly zeroed tensor.
    """
    if p < 0.0 or p > 1.0:
        raise ValueError(f"drop probability has to be between 0 and 1, but got {p}")
    if mode not in ["batch", "row"]:
        raise ValueError(f"mode has to be either 'batch' or 'row', but got {mode}")
    if not training or p == 0.0:
        return input

    survival_rate = 1.0 - p
    if mode == "row":
        size = [input.shape[0]] + [1] * (input.ndim - 1)
    else:
        size = [1] * input.ndim
    noise = torch.empty(size, dtype=input.dtype, device=input.device)
    noise = noise.bernoulli_(survival_rate)
    if survival_rate > 0.0:
        noise.div_(survival_rate)
    return input * noise


torch.fx.wrap("stochastic_depth")


class StochasticDepth(nn.Module):
    """
    See :func:`stochastic_depth`.
    """

    def __init__(self, p: float, mode: str) -> None:
        super().__init__()
        self.p = p
        self.mode = mode

    def forward(self, input: Tensor) -> Tensor:
        return stochastic_depth(input, self.p, self.mode, self.training)

    def __repr__(self) -> str:
        s = f"{self.__class__.__name__}(p={self.p}, mode={self.mode})"
        return s