快捷導(dǎo)航

Pytorch實(shí)現(xiàn)GoogLeNet的方法

更新時(shí)間：2019年08月18日 15:23:46 作者：winycg

今天小編就為大家分享一篇Pytorch實(shí)現(xiàn)GoogLeNet的方法，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧

GoogLeNet也叫InceptionNet，在2014年被提出，如今已到V4版本。GoogleNet比VGGNet具有更深的網(wǎng)絡(luò)結(jié)構(gòu)，一共有22層，但是參數(shù)比AlexNet要少12倍，但是計(jì)算量是AlexNet的4倍，原因就是它采用很有效的Inception模塊，并且沒(méi)有全連接層。

最重要的創(chuàng)新點(diǎn)就在于使用inception模塊，通過(guò)使用不同維度的卷積提取不同尺度的特征圖。左圖是最初的Inception模塊，右圖是使用的1×1得卷積對(duì)左圖的改進(jìn)，降低了輸入的特征圖維度，同時(shí)降低了網(wǎng)絡(luò)的參數(shù)量和計(jì)算復(fù)雜度,稱(chēng)為inception V1。

GoogleNet在架構(gòu)設(shè)計(jì)上為保持低層為傳統(tǒng)卷積方式不變，只在較高的層開(kāi)始用Inception模塊。

inception V2中將5x5的卷積改為2個(gè)3x3的卷積，擴(kuò)大了感受野，原來(lái)是5x5，現(xiàn)在是6x6。Pytorch實(shí)現(xiàn)GoogLeNet(inception V2)：

'''GoogLeNet with PyTorch.'''
import torch
import torch.nn as nn
import torch.nn.functional as F

# 編寫(xiě)卷積+bn+relu模塊
class BasicConv2d(nn.Module):
  def __init__(self, in_channels, out_channals, **kwargs):
    super(BasicConv2d, self).__init__()
    self.conv = nn.Conv2d(in_channels, out_channals, **kwargs)
    self.bn = nn.BatchNorm2d(out_channals)

  def forward(self, x):
    x = self.conv(x)
    x = self.bn(x)
    return F.relu(x)

# 編寫(xiě)Inception模塊
class Inception(nn.Module):
  def __init__(self, in_planes,
         n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes):
    super(Inception, self).__init__()
    # 1x1 conv branch
    self.b1 = BasicConv2d(in_planes, n1x1, kernel_size=1)

    # 1x1 conv -> 3x3 conv branch
    self.b2_1x1_a = BasicConv2d(in_planes, n3x3red, 
                  kernel_size=1)
    self.b2_3x3_b = BasicConv2d(n3x3red, n3x3, 
                  kernel_size=3, padding=1)

    # 1x1 conv -> 3x3 conv -> 3x3 conv branch
    self.b3_1x1_a = BasicConv2d(in_planes, n5x5red, 
                  kernel_size=1)
    self.b3_3x3_b = BasicConv2d(n5x5red, n5x5, 
                  kernel_size=3, padding=1)
    self.b3_3x3_c = BasicConv2d(n5x5, n5x5, 
                  kernel_size=3, padding=1)

    # 3x3 pool -> 1x1 conv branch
    self.b4_pool = nn.MaxPool2d(3, stride=1, padding=1)
    self.b4_1x1 = BasicConv2d(in_planes, pool_planes, 
                 kernel_size=1)

  def forward(self, x):
    y1 = self.b1(x)
    y2 = self.b2_3x3_b(self.b2_1x1_a(x))
    y3 = self.b3_3x3_c(self.b3_3x3_b(self.b3_1x1_a(x)))
    y4 = self.b4_1x1(self.b4_pool(x))
    # y的維度為[batch_size, out_channels, C_out,L_out]
    # 合并不同卷積下的特征圖
    return torch.cat([y1, y2, y3, y4], 1)


class GoogLeNet(nn.Module):
  def __init__(self):
    super(GoogLeNet, self).__init__()
    self.pre_layers = BasicConv2d(3, 192, 
                   kernel_size=3, padding=1)

    self.a3 = Inception(192, 64, 96, 128, 16, 32, 32)
    self.b3 = Inception(256, 128, 128, 192, 32, 96, 64)

    self.maxpool = nn.MaxPool2d(3, stride=2, padding=1)

    self.a4 = Inception(480, 192, 96, 208, 16, 48, 64)
    self.b4 = Inception(512, 160, 112, 224, 24, 64, 64)
    self.c4 = Inception(512, 128, 128, 256, 24, 64, 64)
    self.d4 = Inception(512, 112, 144, 288, 32, 64, 64)
    self.e4 = Inception(528, 256, 160, 320, 32, 128, 128)

    self.a5 = Inception(832, 256, 160, 320, 32, 128, 128)
    self.b5 = Inception(832, 384, 192, 384, 48, 128, 128)

    self.avgpool = nn.AvgPool2d(8, stride=1)
    self.linear = nn.Linear(1024, 10)

  def forward(self, x):
    out = self.pre_layers(x)
    out = self.a3(out)
    out = self.b3(out)
    out = self.maxpool(out)
    out = self.a4(out)
    out = self.b4(out)
    out = self.c4(out)
    out = self.d4(out)
    out = self.e4(out)
    out = self.maxpool(out)
    out = self.a5(out)
    out = self.b5(out)
    out = self.avgpool(out)
    out = out.view(out.size(0), -1)
    out = self.linear(out)
    return out


def test():
  net = GoogLeNet()
  x = torch.randn(1,3,32,32)
  y = net(x)
  print(y.size())

test()

以上這篇Pytorch實(shí)現(xiàn)GoogLeNet的方法就是小編分享給大家的全部?jī)?nèi)容了，希望能給大家一個(gè)參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: