pytorch 中卷积的padding = ‘same’
最近在用pytorch做一个项目,项目中涉及到用卷积部分,平时较常用的框架是tensorflow,keras,在keras的卷积层中,经常会使用到参数padding = ‘same’,即使用“same”的填充方式,但是在pytorch的使用中,我发现pytorch是没有这种填充方式的,自己摸索了一段时间pytorch的框架,下面是用pytorch实现的conv2d中的padding=‘same’的机制。后期会对代码进行详解。
# modify con2d function to use same padding
# code referd to @famssa in 'https://github.com/pytorch/pytorch/issues/3867'
# and tensorflow source code
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__()