VGGNet

感受野

网络结构

代码

model.py

import torch
import torch.nn as nn


class VGG16(nn.Module):
    def __init__(self, num__class):
        super(VGG16, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 64, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2),

            nn.Conv2d(64, 128, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 128, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2),

            nn.Conv2d(128, 256, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2),

            nn.Conv2d(256, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2),

            nn.Conv2d(512, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, 3, 1, 1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2)
        )

        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(512 * 7 * 7, 2048),
            nn.ReLU(inplace=True),

            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            
            nn.Linear(2048, num__class)
        )

    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)
        return x
        

train.py

from model import VGG16
import torch
import torchvision as tv
import torchvision.transforms as transforms
import json

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))
    ])
}

train_set = tv.datasets.ImageFolder(root="C:/Users/14251/Desktop/workspace/VGGNet/flower_data/train",
                                    transform=data_transform["train"])
val_set = tv.datasets.ImageFolder(root="C:/Users/14251/Desktop/workspace/VGGNet/flower_data/train",
                                  transform=data_transform["val"])

train_loader = torch.utils.data.DataLoader(train_set,
                                           batch_size=32,
                                           shuffle=True,
                                           num_workers=0)
val_loader = torch.utils.data.DataLoader(val_set,
                                         batch_size=32,
                                         shuffle=True,
                                         num_workers=0)

flower_list = train_set.class_to_idx
flower_dict = dict((val, key) for key, val in flower_list.items())
json_str = json.dumps(flower_dict, indent=4)
with open("class_indices.json", "w") as json_file:
    json_file.write(json_str)

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

net = VGG16(num__class=5).to(device)

loss_fun = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=0.0002)

best_accurate = 0.0
for epoch in range(10):
    net.train()
    running_loss = 0.0
    for step, train_data in enumerate(train_loader, start=0):
        train_images, train_labels = train_data
        optimizer.zero_grad()
        outputs = net(train_images.to(device))
        loss = loss_fun(outputs, train_labels.to(device))
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        # print train process
        rate = (step + 1) / len(train_loader)
        a = "*" * int(rate * 50)
        b = "." * int((1 - rate) * 50)
        print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(
            int(rate * 100), a, b, loss),
              end="")
    print()

    net.eval()
    accurate = 0.0
    with torch.no_grad():
        for val_data in val_loader:
            val_images, val_labels = val_data
            outputs = net(val_images.to(device))
            pred = torch.max(outputs, dim=1)[1]
            accurate += (pred == val_labels.to(device)).sum().item()
        val_accurate = accurate / len(val_set)
        if (val_accurate > best_accurate):
            best_accurate = val_accurate
            torch.save(net.state_dict(),
                       "C:/Users/14251/Desktop/workspace/VGGNet/VGG_dict.pth")
        print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f' %
              (epoch + 1, running_loss / step, val_accurate))

print("Finished Training")

predict.py

import torch
import json
import torchvision.transforms as transforms
from model import VGG16
from PIL import Image

transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

img = Image.open("C:/Users/14251/Desktop/workspace/VGGNet/test.jpg")
img = transform(img)
img = img.unsqueeze(dim=0)

try:
    json_file = open(
        "C:/Users/14251/Desktop/workspace/VGGNet/class_indices.json", "r")
    class_indices = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)

net = VGG16(num__class=5)
net.load_state_dict(
    torch.load("C:/Users/14251/Desktop/workspace/VGGNet/VGG_dict.pth"))

with torch.no_grad():
    output = net(img).squeeze()
    predict = torch.softmax(output, dim=0)
    predict_cla = torch.argmax(predict).numpy()
    print(class_indices[str(predict_cla)], predict[predict_cla].item())
    

其他版本

model.py

import torch.nn as nn
import torch


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(512*7*7, 2048),
            nn.ReLU(True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(True),
            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 = torch.flatten(x, 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):
    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)
    return model
    

train.py

import torch.nn as nn
from torchvision import transforms, datasets
import json
import os
import torch.optim as optim
from model import vgg
import torch

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(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 path
image_path = data_root + "/data_set/flower_data/"  # flower data set path

train_dataset = datasets.ImageFolder(root=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
train_loader = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size, shuffle=True,
                                           num_workers=0)

validate_dataset = 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)

# 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)

best_acc = 0.0
save_path = './{}Net.pth'.format(model_name)
for epoch in range(30):
    # train
    net.train()
    running_loss = 0.0
    for step, data in enumerate(train_loader, start=0):
        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()
        # print train process
        rate = (step + 1) / len(train_loader)
        a = "*" * int(rate * 50)
        b = "." * int((1 - rate) * 50)
        print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")
    print()

    # validate
    net.eval()
    acc = 0.0  # accumulate accurate number / epoch
    with torch.no_grad():
        for val_data in validate_loader:
            val_images, val_labels = val_data
            optimizer.zero_grad()
            outputs = net(val_images.to(device))
            predict_y = torch.max(outputs, dim=1)[1]
            acc += (predict_y == val_labels.to(device)).sum().item()
        val_accurate = acc / val_num
        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)
        print('[epoch %d] train_loss: %.3f  test_accuracy: %.3f' %
              (epoch + 1, running_loss / step, val_accurate))

print('Finished Training')

predict.py

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

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 = Image.open("../tulip.jpg")
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)

# read class_indict
try:
    json_file = open('./class_indices.json', 'r')
    class_indict = json.load(json_file)
except Exception as e:
    print(e)
    exit(-1)

# create model
model = vgg(model_name="vgg16", num_classes=5)
# load model weights
model_weight_path = "./vgg16Net.pth"
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():
    # predict class
    output = torch.squeeze(model(img))
    predict = torch.softmax(output, dim=0)
    predict_cla = torch.argmax(predict).numpy()
print(class_indict[str(predict_cla)])
plt.show()