VGG16网络的优点：
1.通过堆叠两层3x3的卷积核替代5x5的卷积核， 通过堆叠三层3x3的卷积核替代7x7的卷积核， 原因是拥有相同的感受野，且需要更少的参数：假设输入通道数为C, 则所需要的参数为：
三个3x3的卷积核所需要的参数：3 x 3 x C x C + 3 x 3 x C x C + 3 x 3 x C x C = 27 x C x C
一个7x7的卷积核所需要的参数：7 x 7 x C x C = 49 x C x C
感受野的计算： F(i) = (F(i+1) - 1) x S + K ， F(i)为第i层的感受野， S为步距， K为卷积核的大小。
2.相比于前一代的AlexNet网络，大大减少了神经网络计算时使用的参数。
点击下载花分类数据集
model.py
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, features, num_classes=1000, init_weights=False):super(VGG, self).__init__()# 将特征提取和分类分成两个模块self.features = featuresself.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, 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 7x = torch.flatten(x, start_dim=1)# N x 512*7*7x = self.classifier(x)return xdef _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)if m.bias is not None:nn.init.constant_(m.bias, 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)# 特征提取网络
def make_features(cfg: list):layers = []in_channels = 3for 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# *layers -> 使用非关键字参数将layers中的元素传入Sequential中return nn.Sequential(*layers)# 通过堆叠两层3x3的卷积核替代5x5的卷积核， 通过堆叠三层3x3的卷积核替代7x7的卷积核
# 原因是拥有相同的感受野，且需要更少的参数：假设输入通道数为C, 则所需要的参数为：
# 三个3x3的卷积核：3 x 3 x C x C + 3 x 3 x C x C + 3 x 3 x C x C = 27 x C x C
# 一个7x7的卷积核：7 x 7 x C x C = 49 x C x C
# 感受野的计算： F(i) = (F(i+1) - 1) x S + K F(i)为第i层的感受野， S为步距， K为卷积核的大小
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'],
}def vgg(model_name="vgg16", **kwargs):assert model_name in cfgs, "Warning: model number {} not in cfgs dict!".format(model_name)cfg = cfgs[model_name]model = VGG(make_features(cfg), **kwargs)return modelif __name__ == '__main__':model_name = "vgg16"net = vgg(model_name=model_name, num_classes=5, init_weights=True)train.py
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))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))])}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 = 1nw = 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__':torch.cuda.empty_cache()main()predict.py
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))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))])}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 = 1nw = 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__':torch.cuda.empty_cache()main()class_indices.json
{"0": "daisy","1": "dandelion","2": "roses","3": "sunflowers","4": "tulips"
}
