Pytorch之经典神经网络CNN(七) —— GoogLeNet(InceptionV1)(Bottleneck)(全局平均池化GAP)(1*1卷积)(多尺度)(flower花卉数据集)_googlenet bottleneck

2014年 Google提出的

是和VGG同年出现的，在ILSVRC(ImageNet) 2014中获得冠军，vgg屈居第二

GoogLeNet也称Inception V1。之所以叫GoogLeNet而不叫GoogleNet是为了致敬LeCun的LeNet.

GoogLeNet——含并行连结的网络

在当时取得了非常大的影响， 因为网络的结构变得前所未有， 它颠覆了大家对卷积网络的串联的印象和固定做法， 采用了一种非常有效的 inception 模块， 得到了比 VGG 更深的网络结构， 但是却比 VGG 的参数更少， 因为其去掉了后面的全连接层， 所以参数大大减少， 同时有了很高的计算效率。GoogLeNet 22层，参数量比AlexNet少12倍

它虽然在名字上向LeNet致敬，但在⽹络结构上已经很难看到LeNet的影⼦。 GoogLeNet吸收了NiN中串联⽹络的思想，并在此基础上做了很⼤改进

辅助分类器 Auxiliary Classifier

GoogLeNet用到了辅助分类器。Inception Net一共有22层，除了最后一层的输出结果，中间节点的分类效果也有可能是很好的，所以GoogLeNet将中间某一层的输出作为分类，并以一个较小的权重（0.3）加到最终的分类结果中。一共有2个这样的辅助分类节点。

AlexNet 和 VGG 都只有1个输出层，GoogLeNet 有3个输出层，其中的两个是辅助分类层。

如下图所示，网络主干右边的 两个分支 就是 辅助分类器，其结构一模一样。在训练模型时，将两个辅助分类器的损失乘以权重（论文中是0.3）加到网络的整体损失上，再进行反向传播。

两个辅助分类器的输入分别来自Inception(4a)和Inception(4d)

有没有全连接层

       在分类器之前，采用Network in Network中用Averagepool（平均池化）来代替全连接层的思想，而在avg pool之后，还是添加了一个全连接层，是为了大家做finetune（微调）。

       而无论是VGG还是LeNet、AlexNet，在输出层方面均是采用连续三个全连接层，全连接层的输入是前面卷积层的输出经过reshape得到。有些地方说googlenet去掉了expensive fc layers是指去掉了前两层计算量大的fc层。

      据发现，GoogLeNet将fully-connected layer用avg pooling layer代替后，top-1 accuracy 提高了大约0.6%；然而即使在去除了fully-connected layer后，依然必须dropout。

参数列表

GoogLeNet/Inception 的后续版本

v1： 最早的版本
v2： 加入 batch normalization 加快训练
v3： 对 inception 模块做了调整
v4： 基于 ResNet 加入了 残差连接

Inception模块

GoogLeNet中的基础卷积块叫作Inception块，得名于同名电影《盗梦空间》（Inception）。与NiN块相⽐，这个基础块在结构上更加复杂。

其实左边才是Inception原始的结构，右边的应该叫Inception+降维

Inception块⾥有4条并⾏的线路。前3条线路使⽤窗口⼤小分别是1 × 1、 3 ×3和5 × 5的卷积层来抽取不同空间尺⼨下的信息，其中中间2个线路会对输⼊先做1 × 1卷积来减少输⼊通道数，以降低模型复杂度。第四条线路则使⽤3 × 3最⼤池化层，后接1 × 1卷积层来改变通道数。 4条线路都使⽤了合适的填充来使输⼊与输出的⾼和宽⼀致。最后我们将每条线路的输出在通道维上连结，并输⼊接下来的层中去

注意这里四条路出来的feature不是相加，而是concat到一起

Inception模块的核心思想:  利用不同大小的卷积核实现不同尺度的感知，最后进行融合，可以得到图像更好的表征

Inception 结构的主要思路是怎样用密集成分来近似最优的局部稀疏结构。

网络实现(简化版)

Fashion-MNIST数据集

GoogLeNet 可以看作是很多个 Inception 模块的串联。

GoogLeNet将多个设计精细的Inception块和其他层串串联起来。其中Inception块的通道数分配之⽐比是在ImageNet数据集上通过⼤大量量的实验得来的。

GoogLeNet和它的后继者们一度是ImageNet上最⾼高效的模型之⼀：在类似的测试精度下，它们的计算复杂度往往更更低。
 

代码实现如下图的GoogLenet网络

原论文中使用了多个输出来解决梯度消失的问题， 这里我们只定义一个简单版本的 GoogLeNet， 简化为一个输出

输入的size要是96*96，几通道没关系。不管用CIFAR10还是Fashion-MNIST, 都要resize成96*96的

对于1通道的Fashion-MNIST数据集，size 96*96，我4G显存的GPU的batch_size可以开到32

import torch
from torch import nn, optim
import torch.nn.functional as F
from datetime import datetime
import torchvision
 
class inception(nn.Module):
    def __init__(self, in_channel, out1_1, out2_1, out2_3, out3_1, out3_5, out4_1):
        super(inception, self).__init__()
        #默认stride=1，padding=0
        # 第一条线路
        self.branch1x1 = nn.Sequential(
            nn.Conv2d(in_channel, out1_1, kernel_size=1),
            nn.BatchNorm2d(out1_1, eps=1e-3),
            nn.ReLU(True)
        )
 
        # 第二条线路
        self.branch3x3 = nn.Sequential(
            # conv_relu(in_channel, out2_1, 1),
            nn.Conv2d(in_channel, out2_1, kernel_size=1),
            nn.BatchNorm2d(out2_1, eps=1e-3),
            nn.ReLU(True),
 
            # conv_relu(out2_1, out2_3, 3, padding=1)
            nn.Conv2d(out2_1, out2_3, kernel_size=3, padding=1),
            nn.BatchNorm2d(out2_3, eps=1e-3),
            nn.ReLU(True),
        )
 
 
        #第三条线路
        self.branch5x5 = nn.Sequential(
            # conv_relu(in_channel, out3_1, 1),
            nn.Conv2d(in_channel, out3_1, kernel_size=1),
            nn.BatchNorm2d(out3_1, eps=1e-3),
            nn.ReLU(True),
 
            # conv_relu(out3_1, out3_5, 5, padding=2)
            nn.Conv2d(out3_1, out3_5, kernel_size=5, padding=2),
            nn.BatchNorm2d(out3_5, eps=1e-3),
            nn.ReLU(True),
        )
 
        #第四条线路
        self.branch_pool = nn.Sequential(
            nn.MaxPool2d(3, stride=1, padding=1),
            # conv_relu(in_channel, out4_1, 1)
            nn.Conv2d(in_channel, out4_1, kernel_size=1),
            nn.BatchNorm2d(out4_1, eps=1e-3),
            nn.ReLU(True),
        )
 
    def forward(self, x):
        f1 = self.branch1x1(x)
        f2 = self.branch3x3(x)
        f3 = self.branch5x5(x)
        f4 = self.branch_pool(x)
        output = torch.cat((f1, f2, f3, f4), dim=1)
        return output
 
# test_net = inception(3, 64, 48, 64, 64, 96, 32)
# test_x = torch.tensor(torch.zeros(1, 3, 96, 96))
# print('input shape: {} x {} x {}'.format(test_x.shape[1], test_x.shape[2], test_x.shape[3]))
# test_y = test_net(test_x)
# print('output shape: {} x {} x {}'.format(test_y.shape[1], test_y.shape[2], test_y.shape[3]))
 
class googlenet(nn.Module):
    def __init__(self, in_channel, num_classes, verbose=False):
        super(googlenet, self).__init__()
        self.verbose = verbose
        self.block1 = nn.Sequential(
            # conv_relu(in_channel, out_channel=64, kernel=7, stride=2, padding=3),
            nn.Conv2d(in_channels=in_channel, out_channels=64, kernel_size=7, stride=2, padding=3),
            nn.BatchNorm2d(64, eps=1e-3),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=3, stride=2)
        )
        self.block2 = nn.Sequential(
            # conv_relu(64, 64, kernel=1),
            nn.Conv2d(in_channels=64, out_channels=64, kernel_size=1),
            nn.BatchNorm2d(64, eps=1e-3),
            nn.ReLU(True),
 
            # conv_relu(64, 192, kernel=3, padding=1),
            nn.Conv2d(in_channels=64, out_channels=192, kernel_size=3, padding=1),
            nn.BatchNorm2d(192, eps=1e-3),
            nn.ReLU(True),
 
            nn.MaxPool2d(kernel_size=3, stride=2)
        )
        self.block3 = 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)
        )
        self.block4 = 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(3, 2)
        )
        self.block5 = nn.Sequential(
            inception(832, 256, 160, 320, 32, 128, 128),
            inception(832, 384, 182, 384, 48, 128, 128),
            nn.AvgPool2d(2)
        )
        self.classifier = nn.Linear(1024, num_classes)
 
    def forward(self, x):
        x = self.block1(x)
        if self.verbose:
            print('block 1 output: {}'.format(x.shape))
        x = self.block2(x)
        if self.verbose:
            print('block 2 output: {}'.format(x.shape))
        x = self.block3(x)
        if self.verbose:
            print('block 3 output: {}'.format(x.shape))
        x = self.block4(x)
        if self.verbose:
            print('block 4 output: {}'.format(x.shape))
        x = self.block5(x)
        if self.verbose:
            print('block 5 output: {}'.format(x.shape))
        # print(x.shape)
        #x是[b,1024,1,1]
        x = x.view(x.shape[0], -1)
        #x是[b,1024]
        x = self.classifier(x)
        return x
 
 
def get_acc(output, label):
    total = output.shape[0]
    # output是概率，每行概率最高的就是预测值
    _, pred_label = output.max(1)
    num_correct = (pred_label == label).sum().item()
    return num_correct / total
 
 
batch_size = 32
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize(size=96),
    torchvision.transforms.ToTensor()
])
 
train_set = torchvision.datasets.FashionMNIST(
    root='dataset/',
    train=True,
    download=True,
    transform=transform
)
 
# hand-out留出法划分
train_set, val_set = torch.utils.data.random_split(train_set, [50000, 10000])
 
test_set = torchvision.datasets.FashionMNIST(
    root='dataset/',
    train=False,
    download=True,
    transform=transform
)
 
train_loader = torch.utils.data.DataLoader(
    dataset=train_set,
    batch_size=batch_size,
    shuffle=True
)
val_loader = torch.utils.data.DataLoader(
    dataset=val_set,
    batch_size=batch_size,
    shuffle=True
)
test_loader = torch.utils.data.DataLoader(
    dataset=test_set,
    batch_size=batch_size,
    shuffle=False
)
 
net = googlenet(1,10)
lr = 2e-3
optimizer = optim.Adam(net.parameters(), lr=lr)
critetion = nn.CrossEntropyLoss()
net = net.to(device)
prev_time = datetime.now()
valid_data = val_loader
 
for epoch in range(3):
    train_loss = 0
    train_acc = 0
    net.train()
 
    for inputs, labels in train_loader:
        inputs = inputs.to(device)
        labels = labels.to(device)
 
        # forward
        outputs = net(inputs)
        loss = critetion(outputs, labels)
        # backward
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
 
        train_loss += loss.item()
        train_acc += get_acc(outputs, labels)
        # 最后还要求平均的
 
    # 显示时间
    cur_time = datetime.now()
    h, remainder = divmod((cur_time - prev_time).seconds, 3600)
    m, s = divmod(remainder, 60)
    # time_str = 'Time %02d:%02d:%02d'%(h,m,s)
    time_str = 'Time %02d:%02d:%02d(from %02d/%02d/%02d %02d:%02d:%02d to %02d/%02d/%02d %02d:%02d:%02d)' % (
    h, m, s, prev_time.year, prev_time.month, prev_time.day, prev_time.hour, prev_time.minute, prev_time.second,
    cur_time.year, cur_time.month, cur_time.day, cur_time.hour, cur_time.minute, cur_time.second)
    prev_time = cur_time
 
    # validation
    with torch.no_grad():
        net.eval()
        valid_loss = 0
        valid_acc = 0
        for inputs, labels in valid_data:
            inputs = inputs.to(device)
            labels = labels.to(device)
 
            outputs = net(inputs)
            loss = critetion(outputs, labels)
            valid_loss += loss.item()
            valid_acc += get_acc(outputs, labels)
 
    print("Epoch %d. Train Loss: %f, Train Acc: %f, Valid Loss: %f, Valid Acc: %f,"
          % (epoch, train_loss / len(train_loader), train_acc / len(train_loader), valid_loss / len(valid_data),
             valid_acc / len(valid_data))
          + time_str)
 
    torch.save(net.state_dict(), 'checkpoints/params.pkl')
 
# 测试
with torch.no_grad():
    net.eval()
    correct = 0
    total = 0
    for (images, labels) in test_loader:
        images, labels = images.to(device), labels.to(device)
        output = net(images)
        _, predicted = torch.max(output.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
 
    print("The accuracy of total {} images: {}%".format(total, 100 * correct / total))

可以看到输入的尺寸不断减小， 通道的维度不断增加

flower数据集

http://download.tensorflow.org/example_images/flower_photos.tgz

下载及解压完后应该是这样

数据集进行分类+处理

import os
from shutil import copy
import random
 
def mkfile(file):
    if not os.path.exists(file):
        os.makedirs(file)
 
root_dir = 'dataset/flower/'
file_dir = root_dir + 'flower_photos/'
train_dir = root_dir + 'train/'
val_dir = root_dir + 'val/'
flower_class = [cla for cla in os.listdir(file_dir) if ".txt" not in cla]
 
mkfile(train_dir)
mkfile(val_dir)
for cla in flower_class:
    mkfile(train_dir + cla)
for cla in flower_class:
    mkfile(val_dir + cla)
 
split_rate = 0.1
for cla in flower_class:
    cla_path = file_dir + cla + '/'
    images = os.listdir(cla_path)
    num = len(images)
    eval_index = random.sample(images, k=int(num*split_rate))
    for index, image in enumerate(images):
        if image in eval_index:
            image_path = cla_path + image
            new_path = val_dir + cla
            copy(image_path, new_path)
        else:
            image_path = cla_path + image
            new_path = train_dir + cla
            copy(image_path, new_path)
        print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing bar
    print()
 
print("processing done!")

还要带一个class_indices.json

这个是程序带着的，不是flower数据集中带着的

网络实现

import torch
import torch.nn as nn
from torchvision import transforms, datasets
import json
import torch.optim as optim
import torch.nn.functional as F
 
class BasicConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv2d, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)
        self.relu = nn.ReLU(inplace=True)
 
    def forward(self, x):
        x = self.conv(x)
        x = self.relu(x)
        return x
 
 
class Inception(nn.Module):
    def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
        super(Inception, self).__init__()
 
        self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
 
        self.branch2 = nn.Sequential(
            BasicConv2d(in_channels, ch3x3red, kernel_size=1),
            BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)   # 保证输出大小等于输入大小
        )
 
        self.branch3 = nn.Sequential(
            BasicConv2d(in_channels, ch5x5red, kernel_size=1),
            BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)   # 保证输出大小等于输入大小
        )
 
        self.branch4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
            BasicConv2d(in_channels, pool_proj, kernel_size=1)
        )
 
    def forward(self, x):
        branch1 = self.branch1(x)
        branch2 = self.branch2(x)
        branch3 = self.branch3(x)
        branch4 = self.branch4(x)
 
        outputs = [branch1, branch2, branch3, branch4]
        return torch.cat(outputs, 1)
 
 
 
class GoogLeNet(nn.Module):
    def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
        super(GoogLeNet, self).__init__()
        self.aux_logits = aux_logits
 
        self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
        self.conv2 = BasicConv2d(64, 64, kernel_size=1)
        self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
        self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
        self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
        self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
        self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
        self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
        self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
        self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
        self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
        self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
        self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
 
        self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
        self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
 
        if self.aux_logits:
            self.aux1 = InceptionAux(512, num_classes)
            self.aux2 = InceptionAux(528, num_classes)
 
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.dropout = nn.Dropout(0.4)
        self.fc = nn.Linear(1024, num_classes)
        if init_weights:
            self._initialize_weights()
 
    def forward(self, x):
        # N x 3 x 224 x 224
        x = self.conv1(x)
        # N x 64 x 112 x 112
        x = self.maxpool1(x)
        # N x 64 x 56 x 56
        x = self.conv2(x)
        # N x 64 x 56 x 56
        x = self.conv3(x)
        # N x 192 x 56 x 56
        x = self.maxpool2(x)
 
        # N x 192 x 28 x 28
        x = self.inception3a(x)
        # N x 256 x 28 x 28
        x = self.inception3b(x)
        # N x 480 x 28 x 28
        x = self.maxpool3(x)
        # N x 480 x 14 x 14
        x = self.inception4a(x)
        # N x 512 x 14 x 14
        if self.training and self.aux_logits:    # eval model lose this layer
            aux1 = self.aux1(x)
 
        x = self.inception4b(x)
        # N x 512 x 14 x 14
        x = self.inception4c(x)
        # N x 512 x 14 x 14
        x = self.inception4d(x)
        # N x 528 x 14 x 14
        if self.training and self.aux_logits:    # eval model lose this layer
            aux2 = self.aux2(x)
 
        x = self.inception4e(x)
        # N x 832 x 14 x 14
        x = self.maxpool4(x)
        # N x 832 x 7 x 7
        x = self.inception5a(x)
        # N x 832 x 7 x 7
        x = self.inception5b(x)
        # N x 1024 x 7 x 7
 
        x = self.avgpool(x)
        # N x 1024 x 1 x 1
        x = torch.flatten(x, 1)
        # N x 1024
        x = self.dropout(x)
        x = self.fc(x)
        # N x 1000 (num_classes)
        if self.training and self.aux_logits:   # eval model lose this layer
            return x, aux2, aux1
        return x
 
    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)
 
 
 
 
class InceptionAux(nn.Module):
    def __init__(self, in_channels, num_classes):
        super(InceptionAux, self).__init__()
        self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
        self.conv = BasicConv2d(in_channels, 128, kernel_size=1)  # output[batch, 128, 4, 4]
 
        self.fc1 = nn.Linear(2048, 1024)
        self.fc2 = nn.Linear(1024, num_classes)
 
    def forward(self, x):
        # aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
        x = self.averagePool(x)
        # aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
        x = self.conv(x)
        # N x 128 x 4 x 4
        x = torch.flatten(x, 1)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 2048
        x = F.relu(self.fc1(x), inplace=True)
        x = F.dropout(x, 0.5, training=self.training)
        # N x 1024
        x = self.fc2(x)
        # N x num_classes
        return x
 
 
 
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
data_transform = {
    "train": transforms.Compose([transforms.RandomResizedCrop(224),
                                 transforms.RandomHorizontalFlip(),
                                 transforms.ToTensor(),
                                 transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
                            ),
    "val": transforms.Compose([transforms.Resize((224, 224)),
                               transforms.ToTensor(),
                               transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
                            )
}
 
root = 'dataset/flower/'  # flower data set path
 
train_dataset = datasets.ImageFolder(
        root=root + "train",
        transform=data_transform["train"]
)
 
train_num = len(train_dataset)
 
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open(root + 'class_indices.json', 'w') as json_file:
    json_file.write(json_str)
 
batch_size = 32
train_loader = torch.utils.data.DataLoader(
    dataset=train_dataset,
    batch_size=batch_size, shuffle=True,
    num_workers=0
)
 
validate_dataset = datasets.ImageFolder(
    root=root + "val",
    transform=data_transform["val"]
)
 
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(
    dataset=validate_dataset,
    batch_size=batch_size, shuffle=False,
    num_workers=0
)
 
net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
net.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=3e-4)
 
best_acc = 0.0
save_path = 'checkpoints/googleNet.pth'
for epoch in range(6):
    # train
    net.train()
    running_loss = 0.0
    for step, data in enumerate(train_loader, start=0):
        images, labels = data
        optimizer.zero_grad()
        logits, aux_logits2, aux_logits1 = net(images.to(device))
        loss0 = criterion(logits, labels.to(device))
        loss1 = criterion(aux_logits1, labels.to(device))
        loss2 = criterion(aux_logits2, labels.to(device))
        loss = loss0 + loss1 * 0.3 + loss2 * 0.3
        loss.backward()
        optimizer.step()
 
        # print statistics
        running_loss += loss.item()
        # print train process
        rate = (step + 1) / len(train_loader)
        a = "*" * int(rate * 50)
        b = "." * int((1 - rate) * 50)
        print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")
    print()
 
    # validate
    net.eval()
    acc = 0.0  # accumulate accurate number / epoch
    with torch.no_grad():
        for data_test in validate_loader:
            test_images, test_labels = data_test
            outputs = net(test_images.to(device))  # eval model only have last output layer
            predict_y = torch.max(outputs, dim=1)[1]
            acc += (predict_y == test_labels.to(device)).sum().item()
        accurate_test = acc / val_num
        if accurate_test > best_acc:
            torch.save(net.state_dict(), save_path)
        print('[epoch %d] train_loss: %.3f  val_accuracy: %.3f' %
              (epoch + 1, running_loss / step, accurate_test))
 
print('Finished Training')

predict

predict部分没和主程序写在一起是因为predict的时候就不用辅助分类器的输出了，所以网络结构就变了

所以只能是等训练完模型参数然后再载入进来，这里的载入还是strict=False

import torch
from model import GoogLeNet
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
import json
 
data_transform = transforms.Compose(
    [transforms.Resize((224, 224)),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
 
# load image
# img = Image.open("../tulip.jpg")
img = Image.open("dataset/flower/val/tulips/10791227_7168491604.jpg")
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
 
# read class_indict
try:
    json_file = open('dataset/flower/class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)
 
# create model
model = GoogLeNet(num_classes=5, aux_logits=False)
# load model weights
model_weight_path = "checkpoints/googleNet.pth"
missing_keys, unexpected_keys = model.load_state_dict(torch.load(model_weight_path), strict=False)
model.eval()
with torch.no_grad():
    # predict class
    output = torch.squeeze(model(img))
    predict = torch.softmax(output, dim=0)
    predict_cla = torch.argmax(predict).numpy()
print(class_indict[str(predict_cla)])
plt.show()