GoogLeNet网络一维、二维复现pytorch

已于 2024-05-20 09:23:35 修改
阅读量1.4k 收藏 14
点赞数 5
分类专栏： Pytorch深度学习一维网络 文章标签： 网络 pytorch 人工智能
于 2022-06-16 21:31:21 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-NC-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/chrnhao/article/details/125321988
版权

GoogLeNet复现

2014年诞生了两个大名鼎鼎的网络，一个是VGG另一个就是GoogLeNet，直到包括VGG网络之前，模型的一直都是再纵向上改变，而GoogLeNet在增加模型深度的同时做了宽度上的开拓，并将拥有不同尺寸卷积核的卷积层的输出结果，横向拼接到一起，同时关注不同尺寸的特征。

文章目录


LeNet-AlexNet-ZFNet: LeNet-AlexNet-ZFNet一二维复现pytorch
VGG: VGG一二维复现pytorch
GoogLeNet: GoogLeNet一二维复现pytorch
ResNet: ResNet残差网络一二维复现pytorch-含残差块复现思路分析
DenseNet: DenseNet一二维复现pytorch
Squeeze: SqueezeNet一二维复现pytorch
MobileNet: |从零搭建网络| MobileNet系列网络详解及搭建(学弟提供)
Mnasnet: |从零搭建网络| Mnasnet网络详解及pytorch搭建(学弟提供)
ShuffleNet: |从零搭建网络| ShuffleNet系列网络详解及搭建(学弟提供)
EfficientNet: |从零搭建网络| EfficientNet网络详解及搭建(学弟提供)

下面的是我复现了所有一维卷积神经网络经典模型的链接地址
链接: https://github.com/StChenHaoGitHub/1D-deeplearning-model-pytorch.git

一维模型训练模板代码自己编写已开源
https://github.com/StChenHaoGitHub/1D_Pytorch_Train_demo.git
训练代码讲解博客地址
在这里插入图片描述

GoogLeNet原文链接: Going deeper with convolutions

网络结构图如下，如图一共有9个Inception结构还有3个分类器，由于有三个分类器，最终会把每第一第二分类器的损失乘以0.3加到最终第三个分类器输出的损失上，复现GoogLeNet比麻烦的是这里需要写一个新的损失函数，而其他的复现当中，都是直接用最后一层的损失训练，没有完全复现。

在这里插入图片描述

Inception结构

其中Inception结构论文里也给了两种方式
在这里插入图片描述
a是原始版本，b是减少参数量的版本，a几乎可以说是只有理论上存在，实际使用的都是b版本。接下来开始讨论b版本的inception结构。

Inception有5个部分需要7个参数
1.输入通道数
2.最左侧的卷积核大小为1的卷积的输出通道数
3.从左数第二个分支的两个卷积层中间的过渡通道数和输出通道数
4.从右数第二个分支的两个卷积层中间的过渡通道数和输出通道数
5.最右侧池化层及其链接的一维卷积层的输出通道数

class Inception(torch.nn.Module):
    def __init__(self,in_channels=56,ch1=64,ch3_reduce=96,ch3=128,ch5_reduce=16,ch5=32,pool_proj=32):
        super(Inception, self).__init__()

        self.branch1 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels,ch1,kernel_size=1),
            torch.nn.BatchNorm1d(ch1)
        )

        self.branch3 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch3_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch3_reduce),
            torch.nn.Conv1d(ch3_reduce, ch3, kernel_size=3, padding=1),
            torch.nn.BatchNorm1d(ch3),
        )

        self.branch5 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch5_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch5_reduce),
            torch.nn.Conv1d(ch5_reduce, ch5, kernel_size=5, padding=2),
            torch.nn.BatchNorm1d(ch5),
        )

        self.branch_pool = torch.nn.Sequential(
            torch.nn.MaxPool1d(kernel_size=3,stride=1,padding=1),
            torch.nn.Conv1d(in_channels, pool_proj, kernel_size=1)
        )

    def forward(self,x):
        return torch.cat([self.branch1(x),self.branch3(x),self.branch5(x),self.branch_pool(x)],1)

最后将每一个分支输出的在第二个维度拼接到一起，也就是维度1。批次是维度0，样本点是维度2。

GoogLeNet网络

下面是论文中给出的网络的参数列表
在这里插入图片描述
其中reduce参数就是过渡通道数，根据论文中所给的参数表，加上三个分类器复现代码如下

一维GoogLeNet网络模型实现

import torch

class Inception(torch.nn.Module):
    def __init__(self,in_channels=56,ch1=64,ch3_reduce=96,ch3=128,ch5_reduce=16,ch5=32,pool_proj=32):
        super(Inception, self).__init__()

        self.branch1 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels,ch1,kernel_size=1),
            torch.nn.BatchNorm1d(ch1)
        )

        self.branch3 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch3_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch3_reduce),
            torch.nn.Conv1d(ch3_reduce, ch3, kernel_size=3, padding=1),
            torch.nn.BatchNorm1d(ch3),
        )

        self.branch5 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch5_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch5_reduce),
            torch.nn.Conv1d(ch5_reduce, ch5, kernel_size=5, padding=2),
            torch.nn.BatchNorm1d(ch5),
        )

        self.branch_pool = torch.nn.Sequential(
            torch.nn.MaxPool1d(kernel_size=3,stride=1,padding=1),
            torch.nn.Conv1d(in_channels, pool_proj, kernel_size=1)
        )

    def forward(self,x):
        return torch.cat([self.branch1(x),self.branch3(x),self.branch5(x),self.branch_pool(x)],1)



class GoogLeNet(torch.nn.Module):
    def __init__(self,in_channels=2,in_sample_points=224,classes=5):
        super(GoogLeNet, self).__init__()

        self.features=torch.nn.Sequential(
            torch.nn.Linear(in_sample_points,224),
            torch.nn.Conv1d(in_channels,64,kernel_size=7,stride=2,padding=3),
            torch.nn.MaxPool1d(3,2,padding=1),
            torch.nn.Conv1d(64,192,3,padding=1),
            torch.nn.MaxPool1d(3,2,padding=1),
            Inception(192,64,96,128,16,32,32),
            Inception(256,128,128,192,32,96,64),
            torch.nn.MaxPool1d(3,2,padding=1),
            Inception(480,192,96,208,16,48,64),
        )

        self.classifer_max_pool = torch.nn.MaxPool1d(5,3)

        self.classifer = torch.nn.Sequential(
            torch.nn.Linear(2048,1024),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1024,512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512,classes),
        )

        self.Inception_4b = Inception(512,160,112,224,24,64,64)
        self.Inception_4c = Inception(512,128,128,256,24,64,64)
        self.Inception_4d = Inception(512,112,144,288,32,64,64)


        self.classifer1 = torch.nn.Sequential(
            torch.nn.Linear(2112,1056),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1056,528),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(528,classes),
        )

        self.Inception_4e = Inception(528,256,160,320,32,128,128)
        self.max_pool = torch.nn.MaxPool1d(3,2,1)

        self.Inception_5a = Inception(832,256,160,320,32,128,128)
        self.Inception_5b = Inception(832,384,192,384,48,128,128)

        self.avg_pool = torch.nn.AvgPool1d(7,stride=1)
        self.dropout = torch.nn.Dropout(0.4)
        self.classifer2 = torch.nn.Sequential(
            torch.nn.Linear(1024, 512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512, classes),
        )


    def forward(self,x):
        x = self.features(x)

        y = self.classifer(self.classifer_max_pool(x).view(-1,2048))

        x = self.Inception_4b(x)
        x = self.Inception_4c(x)
        x = self.Inception_4d(x)

        y1 = self.classifer1(self.classifer_max_pool(x).view(-1,2112))

        x = self.Inception_4e(x)
        x = self.max_pool(x)
        x = self.Inception_5a(x)
        x = self.Inception_5b(x)
        x = self.avg_pool(x)
        x = self.dropout(x)
        x = x.view(-1,1024)
        x = self.classifer2(x)

        return x,y,y1

其中x为softmax2分类器输出y1为softmax1分类器输出y为softmax0分类器输出
这里比较特殊的就是需要返回三个输出因此需要配套的损失函数。

GoogLeNet专属损失函数

class GoogLeNetLoss(torch.nn.Module):
    def __init__(self):
        super(GoogLeNetLoss, self).__init__()
        self.CrossEntropyLoss = torch.nn.CrossEntropyLoss()

    def forward(self,data,label):
        c2_loss = self.CrossEntropyLoss(data[0],label)
        c0_loss = self.CrossEntropyLoss(data[1],label)
        c1_loss = self.CrossEntropyLoss(data[2],label)

        loss = c2_loss + 0.3*(c0_loss+c1_loss)

        return loss

完整代码

import torch
from torchsummary import summary

class Inception(torch.nn.Module):
    def __init__(self,in_channels=56,ch1=64,ch3_reduce=96,ch3=128,ch5_reduce=16,ch5=32,pool_proj=32):
        super(Inception, self).__init__()

        self.branch1 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels,ch1,kernel_size=1),
            torch.nn.BatchNorm1d(ch1)
        )

        self.branch3 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch3_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch3_reduce),
            torch.nn.Conv1d(ch3_reduce, ch3, kernel_size=3, padding=1),
            torch.nn.BatchNorm1d(ch3),
        )

        self.branch5 = torch.nn.Sequential(
            torch.nn.Conv1d(in_channels, ch5_reduce, kernel_size=1),
            torch.nn.BatchNorm1d(ch5_reduce),
            torch.nn.Conv1d(ch5_reduce, ch5, kernel_size=5, padding=2),
            torch.nn.BatchNorm1d(ch5),
        )

        self.branch_pool = torch.nn.Sequential(
            torch.nn.MaxPool1d(kernel_size=3,stride=1,padding=1),
            torch.nn.Conv1d(in_channels, pool_proj, kernel_size=1)
        )

    def forward(self,x):
        return torch.cat([self.branch1(x),self.branch3(x),self.branch5(x),self.branch_pool(x)],1)



class GoogLeNet(torch.nn.Module):
    def __init__(self,in_channels=2,in_sample_points=224,classes=5):
        super(GoogLeNet, self).__init__()

        self.features=torch.nn.Sequential(
            torch.nn.Linear(in_sample_points,224),
            torch.nn.Conv1d(in_channels,64,kernel_size=7,stride=2,padding=3),
            torch.nn.MaxPool1d(3,2,padding=1),
            torch.nn.Conv1d(64,192,3,padding=1),
            torch.nn.MaxPool1d(3,2,padding=1),
            Inception(192,64,96,128,16,32,32),
            Inception(256,128,128,192,32,96,64),
            torch.nn.MaxPool1d(3,2,padding=1),
            Inception(480,192,96,208,16,48,64),
        )



        self.classifer_max_pool = torch.nn.MaxPool1d(5,3)

        self.classifer = torch.nn.Sequential(
            torch.nn.Linear(2048,1024),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1024,512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512,classes),
        )

        self.Inception_4b = Inception(512,160,112,224,24,64,64)
        self.Inception_4c = Inception(512,128,128,256,24,64,64)
        self.Inception_4d = Inception(512,112,144,288,32,64,64)


        self.classifer1 = torch.nn.Sequential(
            torch.nn.Linear(2112,1056),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1056,528),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(528,classes),
        )

        self.Inception_4e = Inception(528,256,160,320,32,128,128)
        self.max_pool = torch.nn.MaxPool1d(3,2,1)

        self.Inception_5a = Inception(832,256,160,320,32,128,128)
        self.Inception_5b = Inception(832,384,192,384,48,128,128)

        self.avg_pool = torch.nn.AvgPool1d(7,stride=1)
        self.dropout = torch.nn.Dropout(0.4)
        self.classifer2 = torch.nn.Sequential(
            torch.nn.Linear(1024, 512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512, classes),
        )


    def forward(self,x):
        x = self.features(x)

        y = self.classifer(self.classifer_max_pool(x).view(-1,2048))

        x = self.Inception_4b(x)
        x = self.Inception_4c(x)
        x = self.Inception_4d(x)

        y1 = self.classifer1(self.classifer_max_pool(x).view(-1,2112))

        x = self.Inception_4e(x)
        x = self.max_pool(x)
        x = self.Inception_5a(x)
        x = self.Inception_5b(x)
        x = self.avg_pool(x)
        x = self.dropout(x)
        x = x.view(-1,1024)
        x = self.classifer2(x)

        return x,y,y1

class GoogLeNetLoss(torch.nn.Module):
    def __init__(self):
        super(GoogLeNetLoss, self).__init__()
        self.CrossEntropyLoss = torch.nn.CrossEntropyLoss()

    def forward(self,data,label):
        c2_loss = self.CrossEntropyLoss(data[0],label)
        c0_loss = self.CrossEntropyLoss(data[1],label)
        c1_loss = self.CrossEntropyLoss(data[2],label)

        loss = c2_loss + 0.3*(c0_loss+c1_loss)

        return loss




if __name__ == '__main__':
    model = GoogLeNet()
    input = torch.randn(size=(2,2,224))
    # [c2,c0,c1] = model(input)
    output = model(input)
    criterion = GoogLeNetLoss()
    label = torch.tensor([1,0])
    print(f"损失为:{criterion(output,label)}")
    print(f"输出结果为{output}")
    print(model)
    summary(model=model, input_size=(2, 224), device='cpu')

输出结果如下

损失为:2.53948974609375
输出结果为(tensor([[-0.0974, -0.0311,  0.0815, -0.0201, -0.1416],
        [ 0.3268, -0.1535, -0.0960, -0.0373,  0.0472]],
       grad_fn=<AddmmBackward>), tensor([[ 0.2001, -0.4010, -0.0270, -0.5973,  0.4724],
        [-0.0031, -0.0116,  0.2749, -0.0630, -0.1351]],
       grad_fn=<AddmmBackward>), tensor([[ 0.0689, -0.1227,  0.3872, -0.3770, -0.0234],
        [ 0.0773,  0.8251,  0.1869, -0.2420,  0.2121]],
       grad_fn=<AddmmBackward>))
GoogLeNet(
  (features): Sequential(
    (0): Linear(in_features=224, out_features=224, bias=True)
    (1): Conv1d(2, 64, kernel_size=(7,), stride=(2,), padding=(3,))
    (2): MaxPool1d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (3): Conv1d(64, 192, kernel_size=(3,), stride=(1,), padding=(1,))
    (4): MaxPool1d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (5): Inception(
      (branch1): Sequential(
        (0): Conv1d(192, 64, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv1d(192, 96, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(96, 128, kernel_size=(3,), stride=(1,), padding=(1,))
        (3): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv1d(192, 16, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(16, 32, kernel_size=(5,), stride=(1,), padding=(2,))
        (3): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv1d(192, 32, kernel_size=(1,), stride=(1,))
      )
    )
    (6): Inception(
      (branch1): Sequential(
        (0): Conv1d(256, 128, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv1d(256, 128, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(128, 192, kernel_size=(3,), stride=(1,), padding=(1,))
        (3): BatchNorm1d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv1d(256, 32, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(32, 96, kernel_size=(5,), stride=(1,), padding=(2,))
        (3): BatchNorm1d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv1d(256, 64, kernel_size=(1,), stride=(1,))
      )
    )
    (7): MaxPool1d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (8): Inception(
      (branch1): Sequential(
        (0): Conv1d(480, 192, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv1d(480, 96, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(96, 208, kernel_size=(3,), stride=(1,), padding=(1,))
        (3): BatchNorm1d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv1d(480, 16, kernel_size=(1,), stride=(1,))
        (1): BatchNorm1d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv1d(16, 48, kernel_size=(5,), stride=(1,), padding=(2,))
        (3): BatchNorm1d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv1d(480, 64, kernel_size=(1,), stride=(1,))
      )
    )
  )
  (classifer_max_pool): MaxPool1d(kernel_size=5, stride=3, padding=0, dilation=1, ceil_mode=False)
  (classifer): Sequential(
    (0): Linear(in_features=2048, out_features=1024, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=1024, out_features=512, bias=True)
    (4): Dropout(p=0.5, inplace=False)
    (5): ReLU()
    (6): Linear(in_features=512, out_features=5, bias=True)
  )
  (Inception_4b): Inception(
    (branch1): Sequential(
      (0): Conv1d(512, 160, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(512, 112, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(112, 224, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(512, 24, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(24, 64, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(512, 64, kernel_size=(1,), stride=(1,))
    )
  )
  (Inception_4c): Inception(
    (branch1): Sequential(
      (0): Conv1d(512, 128, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(512, 128, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(128, 256, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(512, 24, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(24, 64, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(512, 64, kernel_size=(1,), stride=(1,))
    )
  )
  (Inception_4d): Inception(
    (branch1): Sequential(
      (0): Conv1d(512, 112, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(512, 144, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(144, 288, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(512, 32, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(32, 64, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(512, 64, kernel_size=(1,), stride=(1,))
    )
  )
  (classifer1): Sequential(
    (0): Linear(in_features=2112, out_features=1056, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=1056, out_features=528, bias=True)
    (4): Dropout(p=0.5, inplace=False)
    (5): ReLU()
    (6): Linear(in_features=528, out_features=5, bias=True)
  )
  (Inception_4e): Inception(
    (branch1): Sequential(
      (0): Conv1d(528, 256, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(528, 160, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(160, 320, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(528, 32, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(32, 128, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(528, 128, kernel_size=(1,), stride=(1,))
    )
  )
  (max_pool): MaxPool1d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (Inception_5a): Inception(
    (branch1): Sequential(
      (0): Conv1d(832, 256, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(832, 160, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(160, 320, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(832, 32, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(32, 128, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(832, 128, kernel_size=(1,), stride=(1,))
    )
  )
  (Inception_5b): Inception(
    (branch1): Sequential(
      (0): Conv1d(832, 384, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv1d(832, 192, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(192, 384, kernel_size=(3,), stride=(1,), padding=(1,))
      (3): BatchNorm1d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv1d(832, 48, kernel_size=(1,), stride=(1,))
      (1): BatchNorm1d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv1d(48, 128, kernel_size=(5,), stride=(1,), padding=(2,))
      (3): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv1d(832, 128, kernel_size=(1,), stride=(1,))
    )
  )
  (avg_pool): AvgPool1d(kernel_size=(7,), stride=(1,), padding=(0,))
  (dropout): Dropout(p=0.4, inplace=False)
  (classifer2): Sequential(
    (0): Linear(in_features=1024, out_features=512, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=512, out_features=5, bias=True)
  )
)
----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Linear-1               [-1, 2, 224]          50,400
            Conv1d-2              [-1, 64, 112]             960
         MaxPool1d-3               [-1, 64, 56]               0
            Conv1d-4              [-1, 192, 56]          37,056
         MaxPool1d-5              [-1, 192, 28]               0
            Conv1d-6               [-1, 64, 28]          12,352
       BatchNorm1d-7               [-1, 64, 28]             128
            Conv1d-8               [-1, 96, 28]          18,528
       BatchNorm1d-9               [-1, 96, 28]             192
           Conv1d-10              [-1, 128, 28]          36,992
      BatchNorm1d-11              [-1, 128, 28]             256
           Conv1d-12               [-1, 16, 28]           3,088
      BatchNorm1d-13               [-1, 16, 28]              32
           Conv1d-14               [-1, 32, 28]           2,592
      BatchNorm1d-15               [-1, 32, 28]              64
        MaxPool1d-16              [-1, 192, 28]               0
           Conv1d-17               [-1, 32, 28]           6,176
        Inception-18              [-1, 256, 28]               0
           Conv1d-19              [-1, 128, 28]          32,896
      BatchNorm1d-20              [-1, 128, 28]             256
           Conv1d-21              [-1, 128, 28]          32,896
      BatchNorm1d-22              [-1, 128, 28]             256
           Conv1d-23              [-1, 192, 28]          73,920
      BatchNorm1d-24              [-1, 192, 28]             384
           Conv1d-25               [-1, 32, 28]           8,224
      BatchNorm1d-26               [-1, 32, 28]              64
           Conv1d-27               [-1, 96, 28]          15,456
      BatchNorm1d-28               [-1, 96, 28]             192
        MaxPool1d-29              [-1, 256, 28]               0
           Conv1d-30               [-1, 64, 28]          16,448
        Inception-31              [-1, 480, 28]               0
        MaxPool1d-32              [-1, 480, 14]               0
           Conv1d-33              [-1, 192, 14]          92,352
      BatchNorm1d-34              [-1, 192, 14]             384
           Conv1d-35               [-1, 96, 14]          46,176
      BatchNorm1d-36               [-1, 96, 14]             192
           Conv1d-37              [-1, 208, 14]          60,112
      BatchNorm1d-38              [-1, 208, 14]             416
           Conv1d-39               [-1, 16, 14]           7,696
      BatchNorm1d-40               [-1, 16, 14]              32
           Conv1d-41               [-1, 48, 14]           3,888
      BatchNorm1d-42               [-1, 48, 14]              96
        MaxPool1d-43              [-1, 480, 14]               0
           Conv1d-44               [-1, 64, 14]          30,784
        Inception-45              [-1, 512, 14]               0
        MaxPool1d-46               [-1, 512, 4]               0
           Linear-47                 [-1, 1024]       2,098,176
          Dropout-48                 [-1, 1024]               0
             ReLU-49                 [-1, 1024]               0
           Linear-50                  [-1, 512]         524,800
          Dropout-51                  [-1, 512]               0
             ReLU-52                  [-1, 512]               0
           Linear-53                    [-1, 5]           2,565
           Conv1d-54              [-1, 160, 14]          82,080
      BatchNorm1d-55              [-1, 160, 14]             320
           Conv1d-56              [-1, 112, 14]          57,456
      BatchNorm1d-57              [-1, 112, 14]             224
           Conv1d-58              [-1, 224, 14]          75,488
      BatchNorm1d-59              [-1, 224, 14]             448
           Conv1d-60               [-1, 24, 14]          12,312
      BatchNorm1d-61               [-1, 24, 14]              48
           Conv1d-62               [-1, 64, 14]           7,744
      BatchNorm1d-63               [-1, 64, 14]             128
        MaxPool1d-64              [-1, 512, 14]               0
           Conv1d-65               [-1, 64, 14]          32,832
        Inception-66              [-1, 512, 14]               0
           Conv1d-67              [-1, 128, 14]          65,664
      BatchNorm1d-68              [-1, 128, 14]             256
           Conv1d-69              [-1, 128, 14]          65,664
      BatchNorm1d-70              [-1, 128, 14]             256
           Conv1d-71              [-1, 256, 14]          98,560
      BatchNorm1d-72              [-1, 256, 14]             512
           Conv1d-73               [-1, 24, 14]          12,312
      BatchNorm1d-74               [-1, 24, 14]              48
           Conv1d-75               [-1, 64, 14]           7,744
      BatchNorm1d-76               [-1, 64, 14]             128
        MaxPool1d-77              [-1, 512, 14]               0
           Conv1d-78               [-1, 64, 14]          32,832
        Inception-79              [-1, 512, 14]               0
           Conv1d-80              [-1, 112, 14]          57,456
      BatchNorm1d-81              [-1, 112, 14]             224
           Conv1d-82              [-1, 144, 14]          73,872
      BatchNorm1d-83              [-1, 144, 14]             288
           Conv1d-84              [-1, 288, 14]         124,704
      BatchNorm1d-85              [-1, 288, 14]             576
           Conv1d-86               [-1, 32, 14]          16,416
      BatchNorm1d-87               [-1, 32, 14]              64
           Conv1d-88               [-1, 64, 14]          10,304
      BatchNorm1d-89               [-1, 64, 14]             128
        MaxPool1d-90              [-1, 512, 14]               0
           Conv1d-91               [-1, 64, 14]          32,832
        Inception-92              [-1, 528, 14]               0
        MaxPool1d-93               [-1, 528, 4]               0
           Linear-94                 [-1, 1056]       2,231,328
          Dropout-95                 [-1, 1056]               0
             ReLU-96                 [-1, 1056]               0
           Linear-97                  [-1, 528]         558,096
          Dropout-98                  [-1, 528]               0
             ReLU-99                  [-1, 528]               0
          Linear-100                    [-1, 5]           2,645
          Conv1d-101              [-1, 256, 14]         135,424
     BatchNorm1d-102              [-1, 256, 14]             512
          Conv1d-103              [-1, 160, 14]          84,640
     BatchNorm1d-104              [-1, 160, 14]             320
          Conv1d-105              [-1, 320, 14]         153,920
     BatchNorm1d-106              [-1, 320, 14]             640
          Conv1d-107               [-1, 32, 14]          16,928
     BatchNorm1d-108               [-1, 32, 14]              64
          Conv1d-109              [-1, 128, 14]          20,608
     BatchNorm1d-110              [-1, 128, 14]             256
       MaxPool1d-111              [-1, 528, 14]               0
          Conv1d-112              [-1, 128, 14]          67,712
       Inception-113              [-1, 832, 14]               0
       MaxPool1d-114               [-1, 832, 7]               0
          Conv1d-115               [-1, 256, 7]         213,248
     BatchNorm1d-116               [-1, 256, 7]             512
          Conv1d-117               [-1, 160, 7]         133,280
     BatchNorm1d-118               [-1, 160, 7]             320
          Conv1d-119               [-1, 320, 7]         153,920
     BatchNorm1d-120               [-1, 320, 7]             640
          Conv1d-121                [-1, 32, 7]          26,656
     BatchNorm1d-122                [-1, 32, 7]              64
          Conv1d-123               [-1, 128, 7]          20,608
     BatchNorm1d-124               [-1, 128, 7]             256
       MaxPool1d-125               [-1, 832, 7]               0
          Conv1d-126               [-1, 128, 7]         106,624
       Inception-127               [-1, 832, 7]               0
          Conv1d-128               [-1, 384, 7]         319,872
     BatchNorm1d-129               [-1, 384, 7]             768
          Conv1d-130               [-1, 192, 7]         159,936
     BatchNorm1d-131               [-1, 192, 7]             384
          Conv1d-132               [-1, 384, 7]         221,568
     BatchNorm1d-133               [-1, 384, 7]             768
          Conv1d-134                [-1, 48, 7]          39,984
     BatchNorm1d-135                [-1, 48, 7]              96
          Conv1d-136               [-1, 128, 7]          30,848
     BatchNorm1d-137               [-1, 128, 7]             256
       MaxPool1d-138               [-1, 832, 7]               0
          Conv1d-139               [-1, 128, 7]         106,624
       Inception-140              [-1, 1024, 7]               0
       AvgPool1d-141              [-1, 1024, 1]               0
         Dropout-142              [-1, 1024, 1]               0
          Linear-143                  [-1, 512]         524,800
         Dropout-144                  [-1, 512]               0
            ReLU-145                  [-1, 512]               0
          Linear-146                    [-1, 5]           2,565
================================================================
Total params: 9,425,087
Trainable params: 9,425,087
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 2.84
Params size (MB): 35.95
Estimated Total Size (MB): 38.79
----------------------------------------------------------------

Process finished with exit code 0

二维GoogleNet网络模型代码实现

import torch
from torchsummary import summary

class Inception(torch.nn.Module):
    def __init__(self,in_channels=56,ch1=64,ch3_reduce=96,ch3=128,ch5_reduce=16,ch5=32,pool_proj=32):
        super(Inception, self).__init__()

        self.branch1 = torch.nn.Sequential(
            torch.nn.Conv2d(in_channels,ch1,kernel_size=1),
            torch.nn.BatchNorm2d(ch1)
        )

        self.branch3 = torch.nn.Sequential(
            torch.nn.Conv2d(in_channels, ch3_reduce, kernel_size=1),
            torch.nn.BatchNorm2d(ch3_reduce),
            torch.nn.Conv2d(ch3_reduce, ch3, kernel_size=3, padding=1),
            torch.nn.BatchNorm2d(ch3)
        )

        self.branch5 = torch.nn.Sequential(
            torch.nn.Conv2d(in_channels, ch5_reduce, kernel_size=1),
            torch.nn.BatchNorm2d(ch5_reduce),
            torch.nn.Conv2d(ch5_reduce, ch5, kernel_size=5, padding=2),
            torch.nn.BatchNorm2d(ch5)
        )

        self.branch_pool = torch.nn.Sequential(
            torch.nn.MaxPool2d(kernel_size=3,stride=1,padding=1),
            torch.nn.Conv2d(in_channels, pool_proj, kernel_size=1)
        )

    def forward(self,x):
        return torch.cat([self.branch1(x),self.branch3(x),self.branch5(x),self.branch_pool(x)],1)



class GoogLeNet(torch.nn.Module):
    def __init__(self,in_channels=3,in_sample_points=224,classes=5):
        super(GoogLeNet, self).__init__()

        self.features=torch.nn.Sequential(
            torch.nn.Linear(in_sample_points,224),
            torch.nn.Conv2d(in_channels,64,kernel_size=7,stride=2,padding=3),
            torch.nn.MaxPool2d(3,2,padding=1),
            torch.nn.Conv2d(64,192,3,padding=1),
            torch.nn.MaxPool2d(3,2,padding=1),
            Inception(192,64,96,128,16,32,32),
            Inception(256,128,128,192,32,96,64),
            torch.nn.MaxPool2d(3,2,padding=1),
            Inception(480,192,96,208,16,48,64)
        )



        self.classifer_max_pool = torch.nn.MaxPool2d(5,3)

        self.classifer = torch.nn.Sequential(
            torch.nn.Linear(8192,1024),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1024,512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512,classes)
        )

        self.Inception_4b = Inception(512,160,112,224,24,64,64)
        self.Inception_4c = Inception(512,128,128,256,24,64,64)
        self.Inception_4d = Inception(512,112,144,288,32,64,64)


        self.classifer1 = torch.nn.Sequential(
            torch.nn.Linear(8448,1056),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(1056,528),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(528,classes)
        )

        self.Inception_4e = Inception(528,256,160,320,32,128,128)
        self.max_pool = torch.nn.MaxPool2d(3,2,1)

        self.Inception_5a = Inception(832,256,160,320,32,128,128)
        self.Inception_5b = Inception(832,384,192,384,48,128,128)

        self.avg_pool = torch.nn.AvgPool2d(7,stride=1)
        self.dropout = torch.nn.Dropout(0.4)
        self.classifer2 = torch.nn.Sequential(
            torch.nn.Linear(1024, 512),
            torch.nn.Dropout(0.5),
            torch.nn.ReLU(),
            torch.nn.Linear(512, classes)
        )


    def forward(self,x):
        x = self.features(x)

        y = self.classifer(self.classifer_max_pool(x).view(-1,8192))

        x = self.Inception_4b(x)
        x = self.Inception_4c(x)
        x = self.Inception_4d(x)

        y1 = self.classifer1(self.classifer_max_pool(x).view(-1,8448))

        x = self.Inception_4e(x)
        x = self.max_pool(x)
        x = self.Inception_5a(x)
        x = self.Inception_5b(x)
        x = self.avg_pool(x)
        x = self.dropout(x)
        x = x.view(-1,1024)
        x = self.classifer2(x)

        return x

class GoogLeNetLoss(torch.nn.Module):
    def __init__(self):
        super(GoogLeNetLoss, self).__init__()
        self.CrossEntropyLoss = torch.nn.CrossEntropyLoss()

    def forward(self,data,label):
        c2_loss = self.CrossEntropyLoss(data[0],label)
        c0_loss = self.CrossEntropyLoss(data[1],label)
        c1_loss = self.CrossEntropyLoss(data[2],label)

        loss = c2_loss + 0.3*(c0_loss+c1_loss)

        return loss



if __name__ == '__main__':
    model = GoogLeNet(in_channels=3)
    x = torch.randn(size=(1,3,224,224))
    # [c2,c0,c1] = model(input)
    output = model(x)
    criterion = GoogLeNetLoss()
    # label = torch.tensor([1,0])
    # print(f"损失为:{criterion(output,label)}")
    print(f"输出结果为{output}")
    print(model)
    summary(model=model, input_size=(3, 224,224))

模型输出：

输出结果为tensor([[ 0.1532,  0.1498,  0.0414, -0.0266,  0.1378]],
       grad_fn=<AddmmBackward>)
GoogLeNet(
  (features): Sequential(
    (0): Linear(in_features=224, out_features=224, bias=True)
    (1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
    (2): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (4): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (5): Inception(
      (branch1): Sequential(
        (0): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv2d(192, 96, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(96, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv2d(192, 16, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
        (3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1))
      )
    )
    (6): Inception(
      (branch1): Sequential(
        (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(128, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(32, 96, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
        (3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
      )
    )
    (7): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (8): Inception(
      (branch1): Sequential(
        (0): Conv2d(480, 192, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch3): Sequential(
        (0): Conv2d(480, 96, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(96, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch5): Sequential(
        (0): Conv2d(480, 16, kernel_size=(1, 1), stride=(1, 1))
        (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): Conv2d(16, 48, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
        (3): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (branch_pool): Sequential(
        (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
        (1): Conv2d(480, 64, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
  (classifer_max_pool): MaxPool2d(kernel_size=5, stride=3, padding=0, dilation=1, ceil_mode=False)
  (classifer): Sequential(
    (0): Linear(in_features=8192, out_features=1024, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=1024, out_features=512, bias=True)
    (4): Dropout(p=0.5, inplace=False)
    (5): ReLU()
    (6): Linear(in_features=512, out_features=5, bias=True)
  )
  (Inception_4b): Inception(
    (branch1): Sequential(
      (0): Conv2d(512, 160, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(112, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (Inception_4c): Inception(
    (branch1): Sequential(
      (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(512, 24, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(24, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (Inception_4d): Inception(
    (branch1): Sequential(
      (0): Conv2d(512, 112, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(112, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(512, 144, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(144, 288, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (classifer1): Sequential(
    (0): Linear(in_features=8448, out_features=1056, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=1056, out_features=528, bias=True)
    (4): Dropout(p=0.5, inplace=False)
    (5): ReLU()
    (6): Linear(in_features=528, out_features=5, bias=True)
  )
  (Inception_4e): Inception(
    (branch1): Sequential(
      (0): Conv2d(528, 256, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(528, 160, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(528, 32, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(528, 128, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (Inception_5a): Inception(
    (branch1): Sequential(
      (0): Conv2d(832, 256, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(832, 160, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(832, 32, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(32, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (Inception_5b): Inception(
    (branch1): Sequential(
      (0): Conv2d(832, 384, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch3): Sequential(
      (0): Conv2d(832, 192, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (3): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch5): Sequential(
      (0): Conv2d(832, 48, kernel_size=(1, 1), stride=(1, 1))
      (1): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): Conv2d(48, 128, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (branch_pool): Sequential(
      (0): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
      (1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1))
    )
  )
  (avg_pool): AvgPool2d(kernel_size=7, stride=1, padding=0)
  (dropout): Dropout(p=0.4, inplace=False)
  (classifer2): Sequential(
    (0): Linear(in_features=1024, out_features=512, bias=True)
    (1): Dropout(p=0.5, inplace=False)
    (2): ReLU()
    (3): Linear(in_features=512, out_features=5, bias=True)
  )
)
----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Linear-1          [-1, 3, 224, 224]          50,400
            Conv2d-2         [-1, 64, 112, 112]           9,472
         MaxPool2d-3           [-1, 64, 56, 56]               0
            Conv2d-4          [-1, 192, 56, 56]         110,784
         MaxPool2d-5          [-1, 192, 28, 28]               0
            Conv2d-6           [-1, 64, 28, 28]          12,352
       BatchNorm2d-7           [-1, 64, 28, 28]             128
            Conv2d-8           [-1, 96, 28, 28]          18,528
       BatchNorm2d-9           [-1, 96, 28, 28]             192
           Conv2d-10          [-1, 128, 28, 28]         110,720
      BatchNorm2d-11          [-1, 128, 28, 28]             256
           Conv2d-12           [-1, 16, 28, 28]           3,088
      BatchNorm2d-13           [-1, 16, 28, 28]              32
           Conv2d-14           [-1, 32, 28, 28]          12,832
      BatchNorm2d-15           [-1, 32, 28, 28]              64
        MaxPool2d-16          [-1, 192, 28, 28]               0
           Conv2d-17           [-1, 32, 28, 28]           6,176
        Inception-18          [-1, 256, 28, 28]               0
           Conv2d-19          [-1, 128, 28, 28]          32,896
      BatchNorm2d-20          [-1, 128, 28, 28]             256
           Conv2d-21          [-1, 128, 28, 28]          32,896
      BatchNorm2d-22          [-1, 128, 28, 28]             256
           Conv2d-23          [-1, 192, 28, 28]         221,376
      BatchNorm2d-24          [-1, 192, 28, 28]             384
           Conv2d-25           [-1, 32, 28, 28]           8,224
      BatchNorm2d-26           [-1, 32, 28, 28]              64
           Conv2d-27           [-1, 96, 28, 28]          76,896
      BatchNorm2d-28           [-1, 96, 28, 28]             192
        MaxPool2d-29          [-1, 256, 28, 28]               0
           Conv2d-30           [-1, 64, 28, 28]          16,448
        Inception-31          [-1, 480, 28, 28]               0
        MaxPool2d-32          [-1, 480, 14, 14]               0
           Conv2d-33          [-1, 192, 14, 14]          92,352
      BatchNorm2d-34          [-1, 192, 14, 14]             384
           Conv2d-35           [-1, 96, 14, 14]          46,176
      BatchNorm2d-36           [-1, 96, 14, 14]             192
           Conv2d-37          [-1, 208, 14, 14]         179,920
      BatchNorm2d-38          [-1, 208, 14, 14]             416
           Conv2d-39           [-1, 16, 14, 14]           7,696
      BatchNorm2d-40           [-1, 16, 14, 14]              32
           Conv2d-41           [-1, 48, 14, 14]          19,248
      BatchNorm2d-42           [-1, 48, 14, 14]              96
        MaxPool2d-43          [-1, 480, 14, 14]               0
           Conv2d-44           [-1, 64, 14, 14]          30,784
        Inception-45          [-1, 512, 14, 14]               0
        MaxPool2d-46            [-1, 512, 4, 4]               0
           Linear-47                 [-1, 1024]       8,389,632
          Dropout-48                 [-1, 1024]               0
             ReLU-49                 [-1, 1024]               0
           Linear-50                  [-1, 512]         524,800
          Dropout-51                  [-1, 512]               0
             ReLU-52                  [-1, 512]               0
           Linear-53                    [-1, 5]           2,565
           Conv2d-54          [-1, 160, 14, 14]          82,080
      BatchNorm2d-55          [-1, 160, 14, 14]             320
           Conv2d-56          [-1, 112, 14, 14]          57,456
      BatchNorm2d-57          [-1, 112, 14, 14]             224
           Conv2d-58          [-1, 224, 14, 14]         226,016
      BatchNorm2d-59          [-1, 224, 14, 14]             448
           Conv2d-60           [-1, 24, 14, 14]          12,312
      BatchNorm2d-61           [-1, 24, 14, 14]              48
           Conv2d-62           [-1, 64, 14, 14]          38,464
      BatchNorm2d-63           [-1, 64, 14, 14]             128
        MaxPool2d-64          [-1, 512, 14, 14]               0
           Conv2d-65           [-1, 64, 14, 14]          32,832
        Inception-66          [-1, 512, 14, 14]               0
           Conv2d-67          [-1, 128, 14, 14]          65,664
      BatchNorm2d-68          [-1, 128, 14, 14]             256
           Conv2d-69          [-1, 128, 14, 14]          65,664
      BatchNorm2d-70          [-1, 128, 14, 14]             256
           Conv2d-71          [-1, 256, 14, 14]         295,168
      BatchNorm2d-72          [-1, 256, 14, 14]             512
           Conv2d-73           [-1, 24, 14, 14]          12,312
      BatchNorm2d-74           [-1, 24, 14, 14]              48
           Conv2d-75           [-1, 64, 14, 14]          38,464
      BatchNorm2d-76           [-1, 64, 14, 14]             128
        MaxPool2d-77          [-1, 512, 14, 14]               0
           Conv2d-78           [-1, 64, 14, 14]          32,832
        Inception-79          [-1, 512, 14, 14]               0
           Conv2d-80          [-1, 112, 14, 14]          57,456
      BatchNorm2d-81          [-1, 112, 14, 14]             224
           Conv2d-82          [-1, 144, 14, 14]          73,872
      BatchNorm2d-83          [-1, 144, 14, 14]             288
           Conv2d-84          [-1, 288, 14, 14]         373,536
      BatchNorm2d-85          [-1, 288, 14, 14]             576
           Conv2d-86           [-1, 32, 14, 14]          16,416
      BatchNorm2d-87           [-1, 32, 14, 14]              64
           Conv2d-88           [-1, 64, 14, 14]          51,264
      BatchNorm2d-89           [-1, 64, 14, 14]             128
        MaxPool2d-90          [-1, 512, 14, 14]               0
           Conv2d-91           [-1, 64, 14, 14]          32,832
        Inception-92          [-1, 528, 14, 14]               0
        MaxPool2d-93            [-1, 528, 4, 4]               0
           Linear-94                 [-1, 1056]       8,922,144
          Dropout-95                 [-1, 1056]               0
             ReLU-96                 [-1, 1056]               0
           Linear-97                  [-1, 528]         558,096
          Dropout-98                  [-1, 528]               0
             ReLU-99                  [-1, 528]               0
          Linear-100                    [-1, 5]           2,645
          Conv2d-101          [-1, 256, 14, 14]         135,424
     BatchNorm2d-102          [-1, 256, 14, 14]             512
          Conv2d-103          [-1, 160, 14, 14]          84,640
     BatchNorm2d-104          [-1, 160, 14, 14]             320
          Conv2d-105          [-1, 320, 14, 14]         461,120
     BatchNorm2d-106          [-1, 320, 14, 14]             640
          Conv2d-107           [-1, 32, 14, 14]          16,928
     BatchNorm2d-108           [-1, 32, 14, 14]              64
          Conv2d-109          [-1, 128, 14, 14]         102,528
     BatchNorm2d-110          [-1, 128, 14, 14]             256
       MaxPool2d-111          [-1, 528, 14, 14]               0
          Conv2d-112          [-1, 128, 14, 14]          67,712
       Inception-113          [-1, 832, 14, 14]               0
       MaxPool2d-114            [-1, 832, 7, 7]               0
          Conv2d-115            [-1, 256, 7, 7]         213,248
     BatchNorm2d-116            [-1, 256, 7, 7]             512
          Conv2d-117            [-1, 160, 7, 7]         133,280
     BatchNorm2d-118            [-1, 160, 7, 7]             320
          Conv2d-119            [-1, 320, 7, 7]         461,120
     BatchNorm2d-120            [-1, 320, 7, 7]             640
          Conv2d-121             [-1, 32, 7, 7]          26,656
     BatchNorm2d-122             [-1, 32, 7, 7]              64
          Conv2d-123            [-1, 128, 7, 7]         102,528
     BatchNorm2d-124            [-1, 128, 7, 7]             256
       MaxPool2d-125            [-1, 832, 7, 7]               0
          Conv2d-126            [-1, 128, 7, 7]         106,624
       Inception-127            [-1, 832, 7, 7]               0
          Conv2d-128            [-1, 384, 7, 7]         319,872
     BatchNorm2d-129            [-1, 384, 7, 7]             768
          Conv2d-130            [-1, 192, 7, 7]         159,936
     BatchNorm2d-131            [-1, 192, 7, 7]             384
          Conv2d-132            [-1, 384, 7, 7]         663,936
     BatchNorm2d-133            [-1, 384, 7, 7]             768
          Conv2d-134             [-1, 48, 7, 7]          39,984
     BatchNorm2d-135             [-1, 48, 7, 7]              96
          Conv2d-136            [-1, 128, 7, 7]         153,728
     BatchNorm2d-137            [-1, 128, 7, 7]             256
       MaxPool2d-138            [-1, 832, 7, 7]               0
          Conv2d-139            [-1, 128, 7, 7]         106,624
       Inception-140           [-1, 1024, 7, 7]               0
       AvgPool2d-141           [-1, 1024, 1, 1]               0
         Dropout-142           [-1, 1024, 1, 1]               0
          Linear-143                  [-1, 512]         524,800
         Dropout-144                  [-1, 512]               0
            ReLU-145                  [-1, 512]               0
          Linear-146                    [-1, 5]           2,565
================================================================
Total params: 24,959,487
Trainable params: 24,959,487
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 55.82
Params size (MB): 95.21
Estimated Total Size (MB): 151.60
----------------------------------------------------------------

Process finished with exit code 0

如果需要训练模板，可以在下面的浩浩的科研笔记中的付费资料购买，赠送所有一维神经网络模型的经典代码，可以在模板中随意切换。

浩浩的科研笔记
关注
专栏目录
【图像超分】论文复现：新手入门！Pytorch实现SRCNN，数据预处理、模型训练、测试、评估全流程详解，注释详细，简单修改就可以训练你自己的图像数据，有训练好的模型下载地址，随取随用
畅游计算机视觉的海洋
03-11 1万+
【图像超分】论文精读：Image Super-Resolution Using Deep Convolutional Networks（SRCNN）请配合上述论文精读文章使用，效果更佳！图像超分辨率SRCNN和FSRCNN复现代码，除基本的网络实现外，还有特征图可视化，PSNR曲线图可视化，测试自己的图像数据等不想理解原理，希望直接跑通然后应用到自己的图像数据的同学，请直接下载上面的代码，有训练好的模型，直接用即可。具体使用方式见代码中的README！有问题来本文评论区留言！准备数据集，以及数据预处理。
GoogLenet网络详解
fakerth的博客
11-17 7248
GoogLenet网络详解
GoogLeNet(V1-V4)Pytorch复现.zip
06-13
【图像分类】一文彻底搞明白GoogLeNet https://blog.csdn.net/hhhhhhhhhhwwwwwwwwww/article/details/117776589?spm=1001.2014.3001.5502
十一、Pytorch复现GoogLeNet
beyond谚语的博客
04-05 590
《PyTorch深度学习实践》课后作业
GoogleNet的pytorch实现
qq_41333847的博客
11-25 306
# -*- coding:utf-8 -*- """ 作者：Refrain 日期：2020.11.24 内容：GoogLeNet with PyTorch. """ import torch.nn as nn import torch class Inception(nn.Module): def __init__(self,in_planes,n1x1,n3x3red,n3x3,n5x5red,n5x5,pool_planes): #n1x1代表卷积核的channel数..
（四）GoogleNet复现
厚积而薄发
06-12 231
复现GoogleNet
pytorch实现GoogLeNet
anxinbuxinan的博客
08-31 295
GoogLeNet（也称为Inception）是由谷歌公司的研究团队于2014年提出的深度卷积神经网络模型。它在ImageNet大规模视觉识别竞赛（ILSVRC）中取得了突出的成绩，在计算机视觉领域引起了广泛的关注。GoogLeNet的名字来源于其创新的Inception模块，该模块采用多个不同尺寸的卷积核进行特征提取，并将这些特征在通道维度上进行拼接，从而能够捕捉多尺度的图像特征。相比于传统的串行结构，Inception模块的并行操作大大减少了参数数量，提高了网络的效率和性能。
pytorch复现CenterNet目标检测项目
05-10
CenterNet的核心思想是将每个物体视为二维平面上的中心点，通过预测这些中心点的位置来实现目标检测。这种方法避免了传统 anchor-based 方法（如YOLO和Faster R-CNN）中复杂的先验框设定，简化了模型结构，提高了...
可能是史上最详细-Faster RCNN Pytorch 复现全纪录
热门推荐
Winshare
07-25 3万+
Faster RCNN 复现 Faster RCNN作为两阶段检测网络发展中最重要的一个网络，基本可以视为检测任务的里程碑性成果。 伴随而生的MaskRCNN，CascadeRCNN都成为了2019年这个时间点上除了各家AI大厂私有网络范围外，支撑很多业务得以开展的基础。所以，Pytorch为基础来从头复现Faster RCNN 网络是非常有必要的，其中包含了太多的Trick和理论中不会包括的先验...
PointNet++论文复现（一）【PontNet网络模型代码详解 - 分类部分】
晨的博客
03-22 1680
PointNet++论文复现（一）【PontNet网络模型代码详解 - 分类部分】
Pytorch搭建常见分类网络模型------VGG、Googlenet、 MobileNetV3、ResNet50（1）
qq_40379132的博客
05-19 2913
常见的分类网络都可以分为两部分，一部分是特征提取部分，另一部分是分类部分。 1、特征提取部分的功能是对输入进来的图片进行特征提取 ， 优秀的特征可以帮助更容易区分目标，所以特征提取部分一般由各类卷积组成，卷积拥有强大的特征提取能力 ； 2、分类部分会利用特征提取部分获取到的特征进行分类 ，分类部分一般由全连接组成， 特征提取部分获取到的特征一般是一维向量，可以直接进行全连接分类。 通常情况下，特征提取部分就是我们平常了解到的各种神经网络，比如VGG、Mobilenet、Resnet等等；而分类部分就是
pytorch 搭建GoogLeNet
Henry的博客
11-07 1422
引入了Inception 结构，在网络在横向上有深度，融合了不同尺度的特征信息使用了 1*1 的卷积核进行降维处理添加了两个辅助分类器帮助训练丢弃全连接层，使用平均池化层，大大减少了模型的参数下面是GoodLeNet 的网络结构图每层网络的参数为：后面的参数代表Inception 结构的配置。
基于pytorch的GoogleNet实现
Qcherry的博客
07-05 440
代码参考B站UP：霹雳吧啦Wz的《深度学习-图像分类篇章》视频，代码根据个人编程习惯及本人自用数据集进行少量改动，欢迎大佬们批评指正。
GoogleNet之PyTorch实现【动手学习深度学习】
皮皮昌的博客
08-25 484
导入必要的模块 import time import torch from torch import nn, optim import torch.nn.functional as F import sys sys.path.append("..") import d2lzh_pytorch as d2l device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') Inception 块 Inception块中可...
王权富贵：GoogLeNet的pytorch实现
a1103688841的博客
04-13 1640
感谢kuangliu，参考自这个项目里面的一篇叫googlenet.py的文档。 先构建一个基本的Inception模块。构造如上图所示，具体代码如下所示。 '''GoogLeNet with PyTorch.''' import torch import torch.nn as nn import torch.nn.functional as F class Inception(...
【机器学习】卷积神经网络----GoogLeNet网络（pytorch）
cxyhjl的博客
12-31 860
代码是一个使用PyTorch实现的GoogLeNet模型，该模型是一个深度卷积神经网络（CNN）用于图像分类任务。1.定义基本卷积模块BasicConv2d 类是一个基本的卷积块，包含一个卷积层、批归一化层和ReLU激活函数。该类用于构建Inception模块中的各分支。# 导入torch库，torch是一个基于Python的科学计算框架，主要用于深度学习 import torch # 导入to...
Inception模块 GooLeNet网络
TranSad的博客
03-19 6161
GoogLeNet 这篇文章打算简单总结一下GoogLeNet网络，其网络结构如下图所示。 我放上面这张图只是为了方便我们大致了解一下它的结构。我知道这样肯定不太能看清每一层具体细节，因为可以发现，GoogLeNet看起来有非常多且复杂的结构，要是清晰地放在这篇文章里恐怕会占很多篇幅，所以具体、清晰的GoogleNet图可以看这里。 与VGG、AlexNet等卷积神经网络相比，GoogLeNet绝对是我们见过的层数最多的网络了，它的网络层数有超过100层。 Inception ...
Pytorch搭建GoogleNet神经网络
最新发布
2301_78820199的博客
04-16 1827
GoogleNet网络搭建详细过程！超清晰！
利用Pytorch实现GoogLeNet网络
AdjsWsgz的博客
10-25 3062
GoogLeNet是2014年Google团队提出的，获得当年ImageNet竞赛分类任务第一名
评论 8
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

浩浩的科研笔记

这我为您答疑发送资源的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值