Source code for openspeech.modules.pointwise_conv1d

# MIT License
#
# Copyright (c) 2021 Soohwan Kim and Sangchun Ha and Soyoung Cho
#
# 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.nn as nn
from torch import Tensor

from openspeech.modules.conv_base import BaseConv1d


class PointwiseConv1d(BaseConv1d):
    r"""
    When kernel size == 1 conv1d, this operation is termed in literature as pointwise convolution.
    This operation often used to match dimensions.

    Args:
        in_channels (int): Number of channels in the input
        out_channels (int): Number of channels produced by the convolution
        stride (int, optional): Stride of the convolution. Default: 1
        padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
        bias (bool, optional): If True, adds a learnable bias to the output. Default: True

    Inputs: inputs
        - **inputs** (batch, in_channels, time): Tensor containing input vector

    Returns: outputs
        - **outputs** (batch, out_channels, time): Tensor produces by pointwise 1-D convolution.
    """
    def __init__(
            self,
            in_channels: int,
            out_channels: int,
            stride: int = 1,
            padding: int = 0,
            bias: bool = True,
    ) -> None:
        super(PointwiseConv1d, self).__init__()
        self.conv = nn.Conv1d(
            in_channels=in_channels,
            out_channels=out_channels,
            kernel_size=1,
            stride=stride,
            padding=padding,
            bias=bias,
        )

    def forward(self, inputs: Tensor) -> Tensor:
        return self.conv(inputs)