论文阅读
论文链接
这个论文section2就讲Alexnet的LRN没有用，果然喷前任的论文才是最好的点子
1、使用3* 3卷积来模拟7* 7和5* 5卷积
2、对于ALexnet中使用的数据增强方法这里有了改进，关于不同大小目标的随机裁剪原图像大小进行了调整，针对原图像大小随机尺度的训练，进行了预置S=384
模型图示
D、E对应的是VGG16、19
下面的图源网络，侵权删
代码实现
model.py
这里把全连接层改成2048了，原论文是4096，跑不动啊= - =
import torch.nn as nn
import torch
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__()
self.features = features
self.classifier = nn.Sequential(
nn.Dropout(p=0.5),
nn.Linear(25088, 2048),
nn.ReLU(True),
nn.Dropout(p=0.5),
nn.Linear(2048, 2048),
nn.ReLU(True),
nn.Dropout(p=0.5),
nn.Linear(2048, num_classes)
)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.features(x)
# N x 512 x 7 x 7
x = x.flatten(start_dim=1)
# N x 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)
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)
def make_features(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'],
}
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 model
train.py
import os
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))
batch_size = 64
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))])}
image_path = '../flower_data'
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
train_num = len(train_dataset)
val_num = len(validate_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size, shuffle=False)
print("using {} images for training, {} images for validation.".format(train_num,
val_num))
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 = 30
best_acc = 0.0
save_path = './{}Net.pth'.format(model_name)
train_steps = len(train_loader)
for epoch in range(epochs):
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for data in train_bar:
images, labels = data
optimizer.zero_grad()
outputs = net(images.to(device))
loss = loss_function(outputs, labels.to(device))
loss.backward()
optimizer.step()
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
epochs,
loss)
net.eval()
acc = 0.0
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 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))])
img_path = "../tulip.jpg"
img = Image.open(img_path)
plt.imshow(img)
img = data_transform(img)
# 添加batchsize维度
img = torch.unsqueeze(img, dim=0)
json_path = './class_indices.json'
json_file = open(json_path, "r")
class_indict = json.load(json_file)
model = vgg(model_name="vgg16", num_classes=5).to(device)
weights_path = "./vgg16Net.pth"
model.load_state_dict(torch.load(weights_path, map_location=device))
model.eval()
with torch.no_grad():
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()
实验结果
这个电脑跑不动，另一个电脑没有windows，换来换去太麻烦，就没跑这个，用CPU跑了跑，代码没有错就发了