在pytorch中实现与TensorFlow类似的same方式padding

前言

TensorFlow中在使用卷积层函数的时候有一个参数padding可以选择same或者vaild，具体可以看之前的这篇文章：https://oldpan.me/archives/tf-keras-padding-vaild-same.而在pytorch中，现在的版本(0.3.1)中还是没有这个功能的，现在我们要在pytorch中实现与TensorFlow相同功能的padding=’same’的操作。

pytorch中padding-Vaild

首先需要说明一点，在pytorch中，如果你不指定padding的大小，在pytorch中默认的padding方式就是vaild。

我们用一段程序来演示一下pytorch中的vaild操作：

根据上图中的描述，我们首先定义一个长度为13的一维向量，然后用核大小为6，步长为5的一维卷积核对其进行卷积操作，由上图很容易看出输出为长度为2的数据（因为只进行了两次卷积操作，12和13被弃用了）。

>>> input = torch.FloatTensor([[[1,2,3,4,5,6,7,8,9,10,11,12,13]]])
>>> input
(0 ,.,.) = 
   1   2   3   4   5   6   7   8   9  10  11  12  13
[torch.FloatTensor of size 1x1x13]   # 输入长度为13
conv = torch.nn.Conv1d(1,1,6,5)      # 定义一维卷积核
>>> input.size()
>>> torch.Size([1, 1, 13])
>>> input = torch.autograd.Variable(input)
>>> input
Variable containing:
(0 ,.,.) = 
   1   2   3   4   5   6   7   8   9  10  11  12  13
[torch.FloatTensor of size 1x1x13]
>>> output = conv(input)
>>> output.size()
>>> torch.Size([1, 1, 2])     # 输出长度为2

由程序结果可以看到pytorch中的默认padding模式是vaild。

pytorch中padding-same

这里我们借用TensorFlow中的核心函数来模仿实现padding=same的效果。

def conv2d_same_padding(input, weight, bias=None, stride=1, padding=1, dilation=1, groups=1):
    # 函数中padding参数可以无视，实际实现的是padding=same的效果
    input_rows = input.size(2)
    filter_rows = weight.size(2)
    effective_filter_size_rows = (filter_rows - 1) * dilation[0] + 1
    out_rows = (input_rows + stride[0] - 1) // stride[0]
    padding_rows = max(0, (out_rows - 1) * stride[0] +
                        (filter_rows - 1) * dilation[0] + 1 - input_rows)
    rows_odd = (padding_rows % 2 != 0)
    padding_cols = max(0, (out_rows - 1) * stride[0] +
                        (filter_rows - 1) * dilation[0] + 1 - input_rows)
    cols_odd = (padding_rows % 2 != 0)

    if rows_odd or cols_odd:
        input = pad(input, [0, int(cols_odd), 0, int(rows_odd)])

    return F.conv2d(input, weight, bias, stride,
                  padding=(padding_rows // 2, padding_cols // 2),
                  dilation=dilation, groups=groups)

自定义这个函数后我们移植pytorch中的Conv2d函数，在其forward中将默认的conv2d函数改为我们的padding-same函数：

import torch.utils.data
from torch.nn import functional as F

import math
import torch
from torch.nn.parameter import Parameter
from torch.nn.functional import pad
from torch.nn.modules import Module
from torch.nn.modules.utils import _single, _pair, _triple

class _ConvNd(Module):

    def __init__(self, in_channels, out_channels, kernel_size, stride,
                 padding, dilation, transposed, output_padding, groups, bias):
        super(_ConvNd, self).__init__()
        if in_channels % groups != 0:
            raise ValueError('in_channels must be divisible by groups')
        if out_channels % groups != 0:
            raise ValueError('out_channels must be divisible by groups')
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.transposed = transposed
        self.output_padding = output_padding
        self.groups = groups
        if transposed:
            self.weight = Parameter(torch.Tensor(
                in_channels, out_channels // groups, *kernel_size))
        else:
            self.weight = Parameter(torch.Tensor(
                out_channels, in_channels // groups, *kernel_size))
        if bias:
            self.bias = Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self):
        n = self.in_channels
        for k in self.kernel_size:
            n *= k
        stdv = 1. / math.sqrt(n)
        self.weight.data.uniform_(-stdv, stdv)
        if self.bias is not None:
            self.bias.data.uniform_(-stdv, stdv)

    def __repr__(self):
        s = ('{name}({in_channels}, {out_channels}, kernel_size={kernel_size}'
             ', stride={stride}')
        if self.padding != (0,) * len(self.padding):
            s += ', padding={padding}'
        if self.dilation != (1,) * len(self.dilation):
            s += ', dilation={dilation}'
        if self.output_padding != (0,) * len(self.output_padding):
            s += ', output_padding={output_padding}'
        if self.groups != 1:
            s += ', groups={groups}'
        if self.bias is None:
            s += ', bias=False'
        s += ')'
        return s.format(name=self.__class__.__name__, **self.__dict__)

class Conv2d(_ConvNd): 

    def __init__(self, in_channels, out_channels, kernel_size, stride=1,
                 padding=0, dilation=1, groups=1, bias=True):
        kernel_size = _pair(kernel_size)
        stride = _pair(stride)
        padding = _pair(padding)
        dilation = _pair(dilation)
        super(Conv2d, self).__init__(
            in_channels, out_channels, kernel_size, stride, padding, dilation,
            False, _pair(0), groups, bias)

    # 修改这里的实现函数
    def forward(self, input):
        return conv2d_same_padding(input, self.weight, self.bias, self.stride,
                        self.padding, self.dilation, self.groups)

然后在实际使用中，调用我们移植过来修改完的函数即可。
亲测可以实现，具体可以到我这个项目源码中查看：https://github.com/Oldpan/faceswap-pytorch

参考资料：
https://github.com/pytorch/pytorch/issues/3867
https://github.com/tensorflow/tensorflow/blob/3c3c0481ec087aca4fa875d6d936f19b31191fc1/tensorflow/core/framework/common_shape_fns.cc#L40-L48
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/kernels/conv_ops.cc#L568-L605