pytorch搭建VGG网络

VGG网络基本介绍参考上一篇： VGG网络及感受野的计算

模型结构

model.py

import torch.nn as nn
import torch


class VGG(nn.Module):
    def __init__(self, features, num_classes=1000, init_weights=False):
        super(VGG, self).__init__()
        self.features = features
        self.classifier = nn.Sequential( # 生成分类网络
            nn.Dropout(p=0.5),
            nn.Linear(512*7*7, 2048), # 展平处理，2048为原论文的一半
            nn.ReLU(True),
            nn.Dropout(p=0.5), # 50%的比率随机失活
            nn.Linear(2048, 2048), #
            nn.ReLU(True),
            nn.Linear(2048, num_classes) # 第三层全连接层
        )
        if init_weights: # 权重初始化
            self._initialize_weights()

    def forward(self, x): #
        # N x 3 x 224 x 224
        x = self.features(x) # 提取特征网络结构，得到输出
        # N x 512 x 7 x 7
        x = torch.flatten(x, start_dim=1) # 展平处理，从第一维开始（第0维是batch）
        # N x 512*7*7
        x = self.classifier(x) # 将特征矩阵输入分类网络结构
        return x

    def _initialize_weights(self):
        for m in self.modules(): # 遍历网络的子模块
            if isinstance(m, nn.Conv2d): # 卷积层
                # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                nn.init.xavier_uniform_(m.weight) # 使用xavier初始化
                if m.bias is not None: # 采用了偏置，将偏置初始化为0
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear): # 卷积层
                nn.init.xavier_uniform_(m.weight)
                # nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)


def make_features(cfg: list): # 提取特征网络结构，传入对应配置的列表
    layers = [] # 存放创建的每一层结构
    in_channels = 3 # RGB彩色图片
    for v in cfg:
        if v == "M": # 最大池化层
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            layers += [conv2d, nn.ReLU(True)]
            in_channels = v
    return nn.Sequential(*layers) # 通过非关键字参数传入进去


cfgs = { # 字典文件，字典的每个key代表模型的配置文件
    # M代表最大池化下采样层
    'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def vgg(model_name="vgg16", **kwargs): # 实例化vgg网络，此处是实例化vgg16模型配置
    try:
        cfg = cfgs[model_name] # 得到配置列表
    except:
        print("Warning: model number {} not in cfgs dict!".format(model_name))
        exit(-1)
    model = VGG(make_features(cfg), **kwargs) # 通过VGG类实例化vgg网络，两个*号表示可变长度的字典变量
    return model

train.py

train.py使用的是花分类数据集，vgg特别大，而本例所采用的花分类的训练集样本特别小，无法充分训练vgg网络

注意：原论文预训练的模型基于ImageNet进行训练，而本例是从头开始训练

很多论文中的预处理方法都有RGB三个通道分别减去[123.68, 116.78, 103.94]，这三个值是对ImageNet图像数据集的所有图片的RGB三个通道的均值，本例预处理未减去这三个值

import torch.nn as nn
from torchvision import transforms, datasets
import json
import os
import torch.optim as optim
from model import vgg
import torch


def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print("using {} device.".format(device))

    data_transform = { # 预处理
        "train": transforms.Compose([transforms.RandomResizedCrop(224), # 随机裁减
                                     transforms.RandomHorizontalFlip(), # 随机反转
                                     transforms.ToTensor(), # 转化成tensor
                                     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]), # 标准化处理
        "val": transforms.Compose([transforms.Resize((224, 224)),
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}

    data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
    image_path = os.path.join(data_root, "data_set", "flower_data")  # flower data set path
    assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
    train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "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('class_indices.json', 'w') as json_file:
        json_file.write(json_str)

    batch_size = 32
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers
    print('Using {} dataloader workers every process'.format(nw))

    train_loader = torch.utils.data.DataLoader(train_dataset,
                                               batch_size=batch_size, shuffle=True,
                                               num_workers=nw)

    validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
                                            transform=data_transform["val"])
    val_num = len(validate_dataset)
    validate_loader = torch.utils.data.DataLoader(validate_dataset,
                                                  batch_size=batch_size, shuffle=False,
                                                  num_workers=nw)
    print("using {} images for training, {} images fot validation.".format(train_num,
                                                                           val_num))

    # test_data_iter = iter(validate_loader)
    # test_image, test_label = test_data_iter.next()

    model_name = "vgg16"
# num_classes类别个数，num_classes和init_weights保存在【model.py】**kwargs中
    net = vgg(model_name=model_name, num_classes=5, init_weights=True)
    net.to(device)
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.0001)

    best_acc = 0.0
    save_path = './{}Net.pth'.format(model_name)
    for epoch in range(30):
        # train
        net.train()
        running_loss = 0.0
        for step, data in enumerate(train_loader, start=0):
            images, labels = data
            optimizer.zero_grad()
            outputs = net(images.to(device))
            loss = loss_function(outputs, labels.to(device))
            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 val_data in validate_loader:
                val_images, val_labels = val_data
                outputs = net(val_images.to(device))
                predict_y = torch.max(outputs, dim=1)[1]
                acc += (predict_y == val_labels.to(device)).sum().item()
            val_accurate = acc / val_num
            if val_accurate > best_acc:
                best_acc = val_accurate
                torch.save(net.state_dict(), save_path)
            print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f' %
                  (epoch + 1, running_loss / step, val_accurate))

    print('Finished Training')


if __name__ == '__main__':
    main()

predict.py

import torch
from model import vgg
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")
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('./class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)

# create model
model = vgg(model_name="vgg16", num_classes=5)
# load model weights
model_weight_path = "./vgg16Net.pth"
model.load_state_dict(torch.load(model_weight_path))
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()