PyTorch深度学习（19）网络结构VGGNet

 VGGNet

网络结构

分类数据：将数据集中10%的图像为验证集Validation，其他为训练集Train

import os
from shutil import copy, rmtree
import random


def mk_file(file_path: str):
    if os.path.exists(file_path):
        # 如果文件夹存在，则先删除原文件夹在重新创建
        rmtree(file_path)
    os.makedirs(file_path)


def main():
    # 保证随机可复现
    random.seed(0)

    # 将数据集中10%的数据划分到验证集中
    split_rate = 0.1

    # 指向你解压后的flower_photos文件夹
    cwd = os.getcwd()
    data_root = os.path.join(cwd, "data_set")
    origin_flower_path = os.path.join(data_root, "flower_photos")
    assert os.path.exists(origin_flower_path), "path '{}' does not exist.".format(origin_flower_path)
    # 获取类型
    flower_class = [cla for cla in os.listdir(origin_flower_path)
                    if os.path.isdir(os.path.join(origin_flower_path, cla))]

    # 建立保存训练集的文件夹
    train_root = os.path.join(data_root, "train")
    mk_file(train_root)
    for cla in flower_class:
        # 建立每个类别对应的文件夹
        mk_file(os.path.join(train_root, cla))

    # 建立保存验证集的文件夹
    val_root = os.path.join(data_root, "val")
    mk_file(val_root)
    for cla in flower_class:
        # 建立每个类别对应的文件夹
        mk_file(os.path.join(val_root, cla))

    for cla in flower_class:
        cla_path = os.path.join(origin_flower_path, cla)
        images = os.listdir(cla_path)
        num = len(images)
        # 随机采样验证集的索引 10%数量为验证集
        eval_index = random.sample(images, k=int(num*split_rate))
        for index, image in enumerate(images):
            if image in eval_index:
                # 将分配至验证集中的文件复制到相应目录
                image_path = os.path.join(cla_path, image)
                new_path = os.path.join(val_root, cla)
                copy(image_path, new_path)
            else:
                # 将分配至训练集中的文件复制到相应目录
                image_path = os.path.join(cla_path, image)
                new_path = os.path.join(train_root, cla)
                copy(image_path, new_path)
            print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="")  # processing bar
        print()

    print("processing done!")


if __name__ == '__main__':
    main()

VGG Class

import torch.nn as nn
import torch

# official pretrain weights
model_urls = {
    'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
    'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth'
}

class VGG(nn.Module):
    def __init__(self, feature, class_num=1000, init_weights=False):
        super(VGG, self).__init__()
        self.feature = feature
        self.classifier = nn.Sequential(
            nn.Linear(512*7*7, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(p=0.5),
            nn.Linear(4096, class_num)
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        # N × 3 × 224 × 224
        x = self.feature(x)
        # N × 512 × 7 × 7
        x = torch.flatten(x, start_dim=1)
        # N × 512 × 7 × 7
        x = self.classifier(x)
        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')
                nn.init.xavier_uniform_(m.weight)  # 初始化卷积核权重
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)   # 将偏置初始化为0
            elif isinstance(m, nn.Linear):
                nn.init.xavier_uniform_(m.weight)
                # nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)


def make_feature(cfg: list):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            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)


cfgs = {
    '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']
}

# 实例化VGG模型
def vgg(model_name="vgg16", **kwargs):
    try:
        cfg = cfgs[model_name]
    except:
        print("warning: model number {} not in cfgs dict!".format(model_name))
        exit(-1)
    model = VGG(make_feature(cfg), **kwargs)
    return model

Training Phase

import torch
import torchvision
import os
import json
import sys
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torch.utils.data.dataloader
from VGGNet import vgg
from tqdm import tqdm    # python进度条

def main():
    data_transform = {
        "train": transforms.Compose([
            transforms.RandomResizedCrop(224),  # 随机裁剪
            transforms.RandomHorizontalFlip(),  # 随机水平翻转
            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))
        ])
    }

    DEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
    print(DEVICE)

    data_root = os.path.abspath(os.path.join(os.getcwd(), ""))  # get data root path
    image_path = data_root + "/data_set/"  # flower data set path
    assert os.path.exists(image_path), "{} path does not exist.".format(image_path)

    train_dataset = torchvision.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 = 2
    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=0)

    validate_dataset = torchvision.datasets.ImageFolder(root=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=0)
    print("using {} images for training, {} images for validation.".format(train_num, val_num))

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

    model_name = "vgg16"
    net = vgg(model_name=model_name, class_num=5, init_weights=True)
    net.to(DEVICE)
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.0001)

    epochs = 30
    best_acc = 0.0
    save_path = './{}Net.pth'.format(model_name)
    train_steps = len(train_loader)
    for epoch in range(epochs):
        # train
        net.train()
        running_loss = 0.0
        train_bar = tqdm(train_loader, file=sys.stdout)
        for step, data in enumerate(train_bar):
            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()

            train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1, epochs, loss)

        # validate
        net.eval()
        acc = 0.0  # accumulate accurate number / epoch
        with torch.no_grad():
            val_bar = tqdm(validate_loader, file=sys.stdout)
            for val_data in val_bar:
                val_images, val_labels = val_data
                outputs = net(val_images.to(DEVICE))
                predict_y = torch.max(outputs, dim=1)[1]
                acc += torch.eq(predict_y, val_labels.to(DEVICE)).sum().item()

        val_accurate = acc / val_num
        print('[epoch %d] train_loss: %.3f  val_accuracy: %.3f' % (epoch + 1, running_loss / train_steps, val_accurate))

        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)

    print('Finished Training')


if __name__ == '__main__':
    main()

Test Phase

使用一张图片来识别是那种类型

import os
import json

import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt

from model import vgg


def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

    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_path = "../tulip.jpg"
    assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
    img = Image.open(img_path)
    plt.imshow(img)
    # [N, C, H, W]
    img = data_transform(img)
    # expand batch dimension
    img = torch.unsqueeze(img, dim=0)

    # read class_indict
    json_path = './class_indices.json'
    assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)

    json_file = open(json_path, "r")
    class_indict = json.load(json_file)
    
    # create model
    model = vgg(model_name="vgg16", num_classes=5).to(device)
    # load model weights
    weights_path = "./vgg16Net.pth"
    assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
    model.load_state_dict(torch.load(weights_path, map_location=device))

    model.eval()
    with torch.no_grad():
        # predict class
        output = torch.squeeze(model(img.to(device))).cpu()
        predict = torch.softmax(output, dim=0)
        predict_cla = torch.argmax(predict).numpy()

    print_res = "class: {}   prob: {:.3}".format(class_indict[str(predict_cla)],
                                                 predict[predict_cla].numpy())
    plt.title(print_res)
    for i in range(len(predict)):
        print("class: {:10}   prob: {:.3}".format(class_indict[str(i)],
                                                  predict[i].numpy()))
    plt.show()


if __name__ == '__main__':
    main()