PyTorch详解经典网络种含并行连结的网络GoogLeNet实现流程

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

class Inception(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(Inception, self).__init__()
        # 路径1
        c1, c2, c3, c4 = out_channels
        self.route1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
        # 路径2
        self.route2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
        self.route2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        # 路径3
        self.route3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
        self.route3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        # 路径4
        self.route4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.route4_2 = nn.Conv2d(in_channels, c4, kernel_size=1)
    def forward(self, x):
        x1 = F.relu(self.route1_1(x))
        x2 = F.relu(self.route2_2(F.relu(self.route2_1(x))))
        x3 = F.relu(self.route3_2(F.relu(self.route3_1(x))))
        x4 = F.relu(self.route4_2(self.route4_1(x)))
        return torch.cat((x1, x2, x3, x4), dim=1) 

# 模型的第一个模块
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),
    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)
                   )

# Inception组成的第二个模块
b2 = 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)
                    )

# Inception组成的第三个模块
b3 = 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)
                    )

# Inception组成的第四个模块
b4 = 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, nn.Linear(1024, 10))
x = torch.randn(1, 1, 96, 96)
for layer in net:
    x = layer(x)
    print(layer.__class__.__name__, "output shape: ", x.shape)

def load_datasets_Cifar10(batch_size, resize=None):
    trans = [transforms.ToTensor()]
    if resize:
        transform = trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    train_data = torchvision.datasets.CIFAR10(root="../data", train=True, transform=trans, download=True)
    test_data = torchvision.datasets.CIFAR10(root="../data", train=False, transform=trans, download=True)
    print("Cifar10 下载完成...")
    return (torch.utils.data.DataLoader(train_data, batch_size, shuffle=True),
            torch.utils.data.DataLoader(test_data, batch_size, shuffle=False))
def load_datasets_FashionMNIST(batch_size, resize=None):
    trans = [transforms.ToTensor()]
    if resize:
        transform = trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    train_data = torchvision.datasets.FashionMNIST(root="../data", train=True, transform=trans, download=True)
    test_data = torchvision.datasets.FashionMNIST(root="../data", train=False, transform=trans, download=True)
    print("FashionMNIST 下载完成...")
    return (torch.utils.data.DataLoader(train_data, batch_size, shuffle=True),
            torch.utils.data.DataLoader(test_data, batch_size, shuffle=False))
def load_datasets(dataset, batch_size, resize):
    if dataset == "Cifar10":
        return load_datasets_Cifar10(batch_size, resize=resize)
    else:
        return load_datasets_FashionMNIST(batch_size, resize=resize)
train_iter, test_iter = load_datasets("", 128, 96) # Cifar10