# Copyright (c) 2018-2020, NVIDIA CORPORATION. All rights reserved.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

import torch
import torch.nn as nn


class LabelSmoothing(nn.Module):
    """
    NLL loss with label smoothing.
    """
    def __init__(self, padding_idx, smoothing=0.0):
        """
        Constructor for the LabelSmoothing module.

        :param padding_idx: index of the PAD token
        :param smoothing: label smoothing factor
        """
        super(LabelSmoothing, self).__init__()
        self.padding_idx = padding_idx
        self.confidence = 1.0 - smoothing
        self.smoothing = smoothing

    def forward(self, x, target):
        logprobs = torch.nn.functional.log_softmax(x, dim=-1,
                                                   dtype=torch.float32)

        non_pad_mask = (target != self.padding_idx)
        nll_loss = -logprobs.gather(dim=-1, index=target.unsqueeze(1))
        nll_loss = nll_loss.squeeze(1)[non_pad_mask]
        smooth_loss = -logprobs.mean(dim=-1)[non_pad_mask]
        loss = self.confidence * nll_loss + self.smoothing * smooth_loss
        return loss.sum()