打赏

GoogLeNet网络——pytorch版

import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l

class Inception(nn.Module):
    # c1-c4是每条路径的输出通道数
    def __init__(self,in_channels,c1,c2,c3,c4,**kwargs):
        super(Inception,self).__init__(**kwargs)
        # 线路1单1x1卷积层
        self.p1_1 = nn.Conv2d(in_channels,c1,kernel_size=1)
        # 线路2,1x1卷积层后接3x3卷积层
        self.p2_1 = nn.Conv2d(in_channels,c2[0],kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0],c2[1],kernel_size=3,padding=1)
        # 线路3,1x1卷积层后接5x5卷积层
        self.p3_1 = nn.Conv2d(in_channels,c3[0],kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0],c3[1],kernel_size=5,padding=2)
        # 线路4,3x3最大汇聚层后接1x1卷积层
        self.p4_1 = nn.MaxPool2d(kernel_size=3,stride=1,padding=1)
        self.p4_2 = nn.Conv2d(in_channels,c4,kernel_size=1)

    def forward(self,x):
        p1 = F.relu(self.p1_1(x))
        p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
        p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
        p4 = F.relu(self.p4_2(self.p4_1(x)))
        # 在通道维度上连结输出
        return torch.cat((p1,p2,p3,p4),dim=1)

# 第一个模块使用64个通道 7x7卷积层
# (96-7+1+6)/2=48
# (48-3+1+2)/2=24
b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

# 第二个模块使用两个卷积层
# 第一个卷积层64个通道 1x1卷积层
# 第二个卷积层将通道数增加到三倍的3x3卷积层
# 24-3+1+2=24
# (24-3+1+2)/2=12
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
                   nn.ReLU(),
                   nn.Conv2d(64, 192, kernel_size=3, padding=1),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

# 第三个模块串联两个Inception块
# 第一个Inception块输出通道为64+128+32+32=256
# 第二个Inception块输出通道为128+192+96+64=480
# (12-3+1+2)/2=6
b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
                   Inception(256, 128, (128, 192), (32, 96), 64),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

# 第四个模块串联5个Inception块
# 第一个通道数192+208+48+64=512
# 第二个通道数160+224+64+64=512
# 第三个通道数128+256+64+64=512
# 第四个通道数112+288+64+64=528
# 第五个通道数256+320+128+128=832
# (6-3+1+2)/2=3
b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
                   Inception(512, 160, (112, 224), (24, 64), 64),
                   Inception(512, 128, (128, 256), (24, 64), 64),
                   Inception(512, 112, (144, 288), (32, 64), 64),
                   Inception(528, 256, (160, 320), (32, 128), 128),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

# 第五个模块通道数256+320+128+128=832,384+384+128+128=1024
b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
                   Inception(832, 384, (192, 384), (48, 128), 128),
                   nn.AdaptiveAvgPool2d((1,1)),
                   nn.Flatten())

net = nn.Sequential(b1, b2, b3, b4, b5, nn.Linear(1024, 10))

X = torch.rand(size=(1, 1, 96, 96))
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape:\t', X.shape)

"""
Sequential output shape:     torch.Size([1, 64, 24, 24])
Sequential output shape:     torch.Size([1, 192, 12, 12])
Sequential output shape:     torch.Size([1, 480, 6, 6])
Sequential output shape:     torch.Size([1, 832, 3, 3])
Sequential output shape:     torch.Size([1, 1024])
Linear output shape:         torch.Size([1, 10])
"""

lr, num_epochs, batch_size = 0.1, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

 

posted @ 2023-08-06 14:47  不像话  阅读(11)  评论(0编辑  收藏  举报