《动手学深度学习》7.4. 含并行连结的网络(GoogLeNet)
1.训练部分
import torch
from torch import nn
from torch.nn import functional as F
from torchsummary import summary
import MyFunction as MF
class Inception(nn.Module):
"""
一个inception模块的四个并行线路如下:
1.一个1x1的卷积,一个小的感受野进行卷积提取特征
2.一个1x1的卷积加上一个3x3的卷积,1x1的卷积降低输入的特征通道,减少参数计算量,然后接一个3x3的卷积做一个较大感受野的卷积
3.—个1x1的卷积加上一个5x5的卷积,作用和第二个一样
4.一个3×3的最大池化加上1x1的卷积,最大池化改变输入的特征排列,1x1的卷积进行特征提取
最后将四个并行线路得到的特征在通道这个维度上拼接在一起
"""
def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
super(Inception, self).__init__(**kwargs)
self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
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)
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)
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)))
return torch.cat((p1, p2, p3, p4), dim=1)
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))
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1), nn.ReLU(),
nn.Conv2d(64, 192, kernel_size=3, padding=1),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
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))
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))
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))
lr, num_epochs, batch_size = 0.1, 10, 128
train_iter, test_iter = MF.load_data_fashion_mnist(batch_size, resize=96)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
MF.train_ch7(net, train_iter, test_iter, num_epochs, lr, device=device)
- 训练结果
2.预测部分
import torch
from torch import nn
from torch.nn import functional as F
import MyFunction as MF
import os
import matplotlib.pyplot as plt
class Inception(nn.Module):
def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
super(Inception, self).__init__(**kwargs)
self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
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)
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)
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)))
return torch.cat((p1, p2, p3, p4), dim=1)
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))
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1), nn.ReLU(),
nn.Conv2d(64, 192, kernel_size=3, padding=1),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
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))
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))
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))
filename = r'./data/GoogLeNet-9.pth'
if os.path.exists(filename):
net.load_state_dict(torch.load(filename))
else:
print(f"No such file or directory: '{filename}'")
lr, num_epochs, batch_size = 0.1, 10, 128
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
train_iter, test_iter = MF.load_data_fashion_mnist(batch_size, resize=96)
MF.predict_ch7(net, test_iter)
plt.show()
|