VGG神经网络搭建实例----pytorch
笔记，感谢B站up：霹雳巴拉Wz
1.搭建模型脚本model.py
import torch.nn as nn
import torch
# 定义分类网络结构（全连接层）
class VGG(nn.Module):
# 初始化函数
# feature是后面make_features函数提取特征网络结构；
# num_classes:分类的类别个数
# 是否对网络权重进行初始化
def __init__(self, features, num_classes=1000, init_weights=False):
super(VGG, self).__init__()
self.features = features
# 通过nn.Sequential函数生成全连接层网络
self.classifier = nn.Sequential(
# 展平处理与全连接之前
nn.Dropout(p=0.5), # 减少过拟合，50%失活神经元
nn.Linear(512*7*7, 2048), # 展平后的参数
nn.ReLU(True), # 激活函数
nn.Dropout(p=0.5),
nn.Linear(2048, 2048), # 第二层全连接层
nn.ReLU(True),
nn.Linear(2048, num_classes) # 输出层
)
if init_weights: # 是否对网络进行初始化
self._initialize_weights()
# 正向传播
def forward(self, x):
# N x 3 x 224 x 224
x = self.features(x) # 进入网络
# N x 512 x 7 x 7
x = torch.flatten(x, start_dim=1) # 展平
# N x 512*7*7
x = self.classifier(x) # 分类
return x
# 初始化权重函数
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)
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)
# 将cfgs网络结构的参数list类型传入
# make_feature 生成提取特征网络结构
def make_features(cfg: list):
layers = [] # 存入结构
in_channels = 3 # 彩色通道
for v in cfg: # 遍历配置列表
if v == "M": # 若是池化层
layers += [nn.MaxPool2d(kernel_size=2, stride=2)] #创建池化
else: # 创建卷积层
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1) # v是参数64
layers += [conv2d, nn.ReLU(True)] # 拼接激活函数
in_channels = v # 深度，为下一层（下一次循环）的in_channels 赋新值
return nn.Sequential(*layers) # 有个*，代表是非关键字传入
# 四个网络结构
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'],
}
# 模型实例化
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) # 第一次参数：feature ，第二个：分类字典和是否初始化参数
return model
四个网络结构
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’],
}
例如：‘vgg11’: [64, ‘M’, 128, ‘M’, 256, 256, ‘M’, 512, 512, ‘M’, 512, 512, ‘M’]
如下图所示A模型结构图： 64：卷积层；‘M’：池化层
2.训练脚本train.py
== 训练脚本和预测脚本代码解释在AlexNet中解释过了==
import os
import json
import torch
import torch.nn as nn
from torchvision import transforms, datasets
import torch.optim as optim
from tqdm import tqdm
from model import vgg
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
# 对数据集处理
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224), # 随机裁剪
transforms.RandomHorizontalFlip(), # 水平翻转
transforms.ToTensor(), # tensor格式
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]), # 标准处理
"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 for 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和init_weights两个参数传递保存到 model.py的vgg(model_name,**kwargs)的第二个参数中
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)
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)
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)
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()
predict.py
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)
print(print_res)
plt.show()
if __name__ == '__main__':
main()