PyTorch深度学习（18）网络结构LeNet、AlexNet

CNN（Convolutional Neural Network）

目标分类  Classification  图像属于哪一类
目标检索  Retrieval  相同种类归为一类
目标检测  Detection 框选且框内是什么，概率是多少
图像分割  Segmentation  图像分为不同区域
无人驾驶  self-driving cars

图像描述 Image Captioning
图像风格迁移 某些图像特征可视化，不同风格应用到类似图中

雏形：LeCun的LeNet(1998)网络结构

Pytorch Tensor的通道顺序：[batch，channel，height，wight]

（1）LeNet

import torch
import torch.nn as nn
import torch.nn.functional as F

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 5)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))   # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)           # output(16, 14, 14)
        x = F.relu(self.conv2(x))   # output(32, 10, 10)
        x = self.pool2(x)           # output(32, 5, 5)
        x = x.view(-1, 32*5*5)      # output(32*5*5)
        x = F.relu(self.fc1(x))     # output(120)
        x = F.relu(self.fc2(x))     # output(84)
        x = self.fc3(x)             # output(10)
        return x


input1 = torch.rand([32, 3, 32, 32])
model = LeNet()
print(model)
output = model(input1)

（2）Train Phase

import torch
import torchvision
import torch.nn as nn
from LeNet import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
import numpy as np
import torch.utils.data.dataloader
import matplotlib.pyplot as plt

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

# 50000张训练图片
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=False, transform=transform)
# 10000张测试图片
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)

# 加载数据
trainLoader = torch.utils.data.DataLoader(trainset, batch_size=36, shuffle=True, num_workers=0)
testLoader = torch.utils.data.DataLoader(testset, batch_size=10000, shuffle=True, num_workers=0)

# 迭代器
test_data_iter = iter(testLoader)
test_image, test_label = test_data_iter.next()

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

net = LeNet()

loss_function = nn.CrossEntropyLoss()
optim = optim.Adam(net.parameters(), lr=0.001)

# 官方显示图片代码
# def imshow(img):
#     img = img / 2 + 0.5 # unnormalize
#     npimg = img.numpy()
#     plt.imshow(np.transpose(npimg, (1, 2, 0)))
#     plt.show()
#
# # print label
# print(' '.join('%5s' % classes[test_label[j]] for j in range(4)))
# # show image
# imshow(torchvision.utils.make_grid(test_image))

for epoch in range(5):
    running_loss = 0.0
    for step, data in enumerate(trainLoader, start=0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data
        # zero the parameter gradients
        optim.zero_grad()
        # forward + backward + optimize
        outputs = net(inputs)
        loss = loss_function(outputs, labels)
        loss.backward()
        optim.step()

        # print statistics
        running_loss += loss.item()
        if step % 500 == 499: # print every 500 mini-batches
            with torch.no_grad():
                outputs = net(test_image) # [batch, 10]
                predict_y = torch.max(outputs, dim=1)[1]
                accuracy = (predict_y == test_label).sum().item() / test_label.size(0)

                print('[%d, %5d] train_loss: %.3f test_accuracy:%.3f' %
                      (epoch + 1, step + 1, running_loss / 500, accuracy))
                running_loss = 0.0

print('Finished Training')

save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)

# GPU训练
import torchvision
import torch
from LeNet import LeNet
from torchvision import transforms
import torch.utils.data.dataloader
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as opt

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

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

net = LeNet()
net.to(device)
loss_function = torch.nn.CrossEntropyLoss()
optimizer = opt.Adam(net.parameters(), lr=0.001)

def main():
    print('---%s' % device)

    train_data = torchvision.datasets.CIFAR10(root='../dataset/cifar_data', train=True, transform=transform, download=False)
    test_data = torchvision.datasets.CIFAR10(root='../dataset/cifar_data', train=False, transform=transform, download=False)

    train_loader = torch.utils.data.DataLoader(train_data, batch_size=32, shuffle=True, num_workers=0)
    test_loader = torch.utils.data.DataLoader(test_data, batch_size=10000, shuffle=True, num_workers=0)

    test_iter = iter(test_loader)
    test_images, test_labels = test_iter.next()

    for epoch in range(5):
        running_loss = 0.0
        for step, data in enumerate(train_loader, start=0):
            inputs, labels = data
            optimizer.zero_grad()
            inputs = inputs.to(device)
            labels = labels.to(device)
            outputs = net(inputs)
            loss = loss_function(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()

            if step % 500 == 499:
                with torch.no_grad():
                    test_images = test_images.to(device)
                    test_labels = test_labels.to(device)
                    outputs = net(test_images)
                    predict_y = torch.max(outputs, dim=1)[1]
                    accuracy = (predict_y == test_labels).sum().item() / test_labels.size(0)
                    print('%d  %3d  summary loss=%.3f  accuracy=%.3f' % (epoch + 1, step + 1, running_loss, accuracy))

    save_pth()     # 保存路径

def imshow(img):
    img = img / 2 + 0.5  # normalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

def save_pth():
    save_path = './Lenet.pth'
    torch.save(net.state_dict(), save_path)


if __name__ == '__main__':
    main()

（3）Test Phase

import torch
import torchvision.transforms as transforms
from PIL import Image
from LeNet import LeNet

transform = transforms.Compose(
    [transforms.Resize((32, 32)),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

net = LeNet()
net.load_state_dict(torch.load('Lenet.pth'))
im = Image.open('image name')
im = transform(im) # [C, H, W]
im = torch.unsqueeze(im, dim=0) # [N, C, H, W]

with torch.no_grad():
    outputs = net(im)
    predict = torch.max(outputs, dim=1)[1].data.numpy()
    predict = torch.softmax(outputs, dim=1)
print(classes[int(predict)])

AlexNet

2012年ISLVRC2012（ImageNet Large Scale Visual Recognition Challenge）竞赛冠军网络，分类准确率由传统的70%+提升到80%+。由Hinton和其学生Alex Krizhevsky设计的。

ISLVRC  用于数据分类

• ISLVRC 2012
• 训练集：1281167张已标注图片
• 验证集：50000张已标注图片
• 测试集：100000张未标注图片

 亮点：

1. 首次利用GPU进行网络加速训练
2. 使用了ReLU激活函数，而不是传统Sigmoid激活函数及Tanh激活函数
3. 使用了LRN局部响应归一化
4. 在全连接层的前两层中使用了Dropout随机失活神经元操作，减少过拟合

layer_name	kernel_size	kernel_num	padding	stride
Conv1	11	96	[1, 2]	4
Maxpool1	3	None	0	2
Conv2	5	256	[2, 2]	1
Maxpool2	3	None	0	2
Conv3	3	384	[1, 1]	1
Conv4	3	384	[1, 1]	1
Conv5	3	256	[1, 1]	1
Maxpool3	3	None	0	2
FC1	2048	None	None	None
FC2	2048	None	None	None
FC3	1000	None	None	None

AlexNet

import torch.nn as nn
import torch


class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[48, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[48, 27, 27]
            nn.Conv2d(48, 128, kernel_size=5, padding=2),           # output[128, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 13, 13]
            nn.Conv2d(128, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 128, kernel_size=3, padding=1),          # output[128, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(128 * 6 * 6, 2048),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            nn.Linear(2048, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        x = self.features(x)
        x = torch.flatten(x, start_dim=1)
        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')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)

Train

import os
import sys
import json

import torch
import torch.nn as nn
from torchvision import transforms, datasets, utils
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim
from tqdm import tqdm

from model import AlexNet


def 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)),  # cannot 224, must (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=4, 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()
    #
    # def imshow(img):
    #     img = img / 2 + 0.5  # unnormalize
    #     npimg = img.numpy()
    #     plt.imshow(np.transpose(npimg, (1, 2, 0)))
    #     plt.show()
    #
    # print(' '.join('%5s' % cla_dict[test_label[j].item()] for j in range(4)))
    # imshow(utils.make_grid(test_image))

    net = AlexNet(num_classes=5, init_weights=True)

    net.to(device)
    loss_function = nn.CrossEntropyLoss()
    # pata = list(net.parameters())
    optimizer = optim.Adam(net.parameters(), lr=0.0002)

    epochs = 10
    save_path = './AlexNet.pth'
    best_acc = 0.0
    train_steps = len(train_loader)
    for epoch in range(epochs):
        # train
        net.train()
        running_loss = 0.0
        train_bar = tqdm(train_loader, file=sys.stdout)
        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, file=sys.stdout)
            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

import os
import json

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

from model import AlexNet


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 = AlexNet(num_classes=5).to(device)

    # load model weights
    weights_path = "./AlexNet.pth"
    assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
    model.load_state_dict(torch.load(weights_path))

    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)
    for i in range(len(predict)):
        print("class: {:10}   prob: {:.3}".format(class_indict[str(i)],
                                                  predict[i].numpy()))
    plt.show()


if __name__ == '__main__':
    main()