VGG16網絡結構及代碼

下圖為VGG網絡結構圖，最常用的就是表中的D結構，16層結構（13層卷積+3層全連接層），卷積的stride為1，padding為1，maxpool的大小為2，stride為2（池化只改變圖像的大小，不改變圖像的深度）

vgg網絡結構可以看作兩部分：特征提取網絡（連接層之前）+分類網絡（3層全連接層）

VGG模型搭建

VGG模型一共分為兩部分，特征提取部分和分類網絡部分，我們分別進行搭建

特征提取網絡

1、定義字典文件，定義了四個網絡結構

cfgs = { 'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'], # 列表的數字代表卷積層卷積核的個數，字符M代表池化層的結構'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'], }

2、定義一個函數，生成vgg網絡第一部分：特征提取網絡

def make_features(cfg: list): # 傳入一個配置變量layers = [] # 定義一個空列表in_channels = 3for v in cfg:if v == "M": # 判斷是否是池化層layers += [nn.MaxPool2d(kernel_size=2, stride=2)]else:conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1) # v表示輸出通道layers += [conv2d, nn.ReLU(True)]in_channels = v # 卷積之后，輸出通道變為vreturn nn.Sequential(*layers) # *layers代表通過非關鍵字參數的形式傳入進去

分類網絡

1、定義VGG類

# vgg類 class VGG(nn.Module): # features代表提取特征網絡def __init__(self, features, num_classes=1000, init_weights=False):super(VGG, self).__init__()self.features = featuresself.classifier = nn.Sequential(nn.Dropout(p=0.5), # 減少過擬合，50%比例隨機失活神經元nn.Linear(512*7*7, 4096),nn.ReLU(True),nn.Dropout(p=0.5),nn.Linear(4096, 4096),nn.ReLU(True),nn.Linear(4096, num_classes))if init_weights:self._initialize_weights()def forward(self, x):# N x 3 x 224 x 224x = self.features(x)# N x 512 x 7 x 7 展平操作x = torch.flatten(x, start_dim=1) # 從第一個維度開始展平，第0個維度是batch# N x 512*7*7x = self.classifier(x)return x# 初始化權重函數，會便利網絡的每一個子模塊，也就是遍歷每一層def _initialize_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d): # 如果當前層為卷積層# nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')nn.init.xavier_uniform_(m.weight) # 初始化卷積核參數if m.bias is not None: # 如果卷積核有偏置，設置偏置為0nn.init.constant_(m.bias, 0)elif isinstance(m, nn.Linear): # 如果當前層為全連接層nn.init.xavier_uniform_(m.weight)# nn.init.normal_(m.weight, 0, 0.01)nn.init.constant_(m.bias, 0)

2、實例化vgg

# 實例化vgg 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_features(cfg), **kwargs) # **kwargs可變長度的字典變量return modelvgg_model = vgg(model_name='vgg13')

VGG訓練

import os import jsonimport torch import torch.nn as nn from torchvision import transforms, datasets import torch.optim as optim from tqdm import tqdmfrom model import vggdef main():device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")print("using {} device.".format(device)) # 數據預處理data_transform = {"train": transforms.Compose([transforms.RandomResizedCrop(224), # 隨即裁剪transforms.RandomHorizontalFlip(), # 隨機翻轉transforms.ToTensor(), # 轉為tensortransforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),# 標準化處理"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 pathimage_path = os.path.join(data_root, "data_set", "flower_data") # flower data set pathassert 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_idxcla_dict = dict((val, key) for key, val in flower_list.items())# write dict into json filejson_str = json.dumps(cla_dict, indent=4)with open('class_indices.json', 'w') as json_file:json_file.write(json_str)batch_size = 32nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workersprint('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 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, num_classes=5, init_weights=True)net.to(device)loss_function = nn.CrossEntropyLoss()optimizer = optim.Adam(net.parameters(), lr=0.0001)epochs = 30best_acc = 0.0save_path = './{}Net.pth'.format(model_name)train_steps = len(train_loader)for epoch in range(epochs):# trainnet.train()running_loss = 0.0train_bar = tqdm(train_loader)for step, data in enumerate(train_bar):images, labels = dataoptimizer.zero_grad()outputs = net(images.to(device))loss = loss_function(outputs, labels.to(device))loss.backward()optimizer.step()# print statisticsrunning_loss += loss.item()train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,epochs,loss)# validatenet.eval()acc = 0.0 # accumulate accurate number / epochwith torch.no_grad():val_bar = tqdm(validate_loader)for val_data in val_bar:val_images, val_labels = val_dataoutputs = 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_numprint('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %(epoch + 1, running_loss / train_steps, val_accurate))if val_accurate > best_acc:best_acc = val_accuratetorch.save(net.state_dict(), save_path)print('Finished Training')if __name__ == '__main__':main()

VGG預測

import os import jsonimport torch from PIL import Image from torchvision import transforms import matplotlib.pyplot as pltfrom model import vggdef 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 imageimg_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 dimensionimg = torch.unsqueeze(img, dim=0)# read class_indictjson_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 modelmodel = vgg(model_name="vgg16", num_classes=5).to(device)# load model weightsweights_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 classoutput = 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)print(print_res)plt.show()if __name__ == '__main__':main()

參考視頻：https://www.bilibili.com/video/BV1i7411T7ZN?spm_id_from=333.999.0.0

總結

以上是生活随笔為你收集整理的经典卷积神经网络---VGG16网络的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。