深度学习-AlexNet代码实现

数据扩充：Data augmentation

由于神经网络算法是基于数据驱动的，因此，有一种观点认为神经网络是靠数据喂出来的，如果能够增加训练数据，提供海量数据进行训练，则能够有效提升算法的准确率，因为这样可以避免过拟合，从而可以进一步增大、加深网络结构。而当训练数据有限时，可以通过一些变换从已有的训练数据集中生成一些新的数据，以快速地扩充训练数据。
其中，最简单、通用的图像数据变形的方式：水平翻转图像，从原始图像中随机裁剪、平移变换，颜色、光照变换。

训练过程

import os 
import sys
import json 
import torch
import torch.nn as nn
from torchvision import transforms, datasets 
import torch.optim as optim 
from tqdm import tqdm
from classic_models.alexnet import AlexNet  
from classic_models.googlenet_v1 import  GoogLeNet
import os
import json

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

# mac m1 电脑选择mps GPU
def try_gpu(i=0):
    if torch.cuda.device_count() >= i + 1:
        return torch.device(f'cuda:{i}')
    try:
        return torch.device('mps')
    except:
        return torch.device('cpu')
    
def main():
    # 判断可用设备
    device = try_gpu()
    print("using {} device.".format(device))

    # 注意改成自己的数据集路径
    data_path = '/Users/jiangxiyu/根目录/深度学习/flower'
    assert os.path.exists(data_path), "{} path does not exist.".format(data_path) 

    # 数据预处理与增强
    """ 
    ToTensor()能够把灰度范围从0-255变换到0-1之间的张量.
    transform.Normalize()则把0-1变换到(-1,1). 具体地说, 对每个通道而言, Normalize执行以下操作: image=(image-mean)/std
    其中mean和std分别通过(0.5,0.5,0.5)和(0.5,0.5,0.5)进行指定。原来的0-1最小值0则变成(0-0.5)/0.5=-1; 而最大值1则变成(1-0.5)/0.5=1. 
    也就是一个均值为0, 方差为1的正态分布. 这样的数据输入格式可以使神经网络更快收敛。
    """
    data_transform = {
        "train": transforms.Compose([transforms.Resize(224),
                                     transforms.CenterCrop(224),
                                     transforms.ToTensor(),
                                     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),

        "val": transforms.Compose([transforms.Resize((224, 224)),  # val不需要任何数据增强
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}


    # 使用ImageFlolder加载数据集中的图像，并使用指定的预处理操作来处理图像， ImageFlolder会同时返回图像和对应的标签。 (image path, class_index) tuples
    train_dataset = datasets.ImageFolder(root=os.path.join(data_path, "train"), transform=data_transform["train"])
    validate_dataset = datasets.ImageFolder(root=os.path.join(data_path, "val"), transform=data_transform["val"])
    train_num = len(train_dataset)
    val_num = len(validate_dataset)

    # 使用class_to_idx给类别一个index，作为训练时的标签： {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
    flower_list = train_dataset.class_to_idx
    # 创建一个字典，存储index和类别的对应关系，在模型推理阶段会用到。
    cla_dict = dict((val, key) for key, val in flower_list.items())
    # 将字典写成一个json文件
    json_str = json.dumps(cla_dict, indent=4)
    with open( os.path.join(data_path, 'class_indices.json') , 'w') as json_file:
        json_file.write(json_str)

    batch_size = 64 # batch_size大小，是超参，可调，如果模型跑不起来，尝试调小batch_size
 
    # 使用 DataLoader 将 ImageFloder 加载的数据集处理成批量（batch）加载模式
    train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True )
    validate_loader = torch.utils.data.DataLoader(validate_dataset, batch_size=4, shuffle=False ) # 注意，验证集不需要shuffle
    print("using {} images for training, {} images for validation.".format(train_num, val_num))
    
    # 实例化模型，并送进设备
    net = AlexNet(num_classes = 5,init_weights=True)
    net.to(device)

    # 指定损失函数用于计算损失；指定优化器用于更新模型参数；指定训练迭代的轮数，训练权重的存储地址
    loss_function = nn.CrossEntropyLoss() # MSE
    optimizer = optim.Adam(net.parameters(), lr=0.0002)
    epochs = 70
    save_path = os.path.abspath(os.path.join(os.getcwd(), './results/weights/alexnet')) 
    if not os.path.exists(save_path):    
        os.makedirs(save_path)
 
    best_acc = 0.0 # 初始化验证集上最好的准确率，以便后面用该指标筛选模型最优参数。  
    for epoch in range(epochs):
        ############################################################## train ######################################################
        net.train() 
        acc_num = torch.zeros(1).to(device)    # 初始化，用于计算训练过程中预测正确的数量
        sample_num = 0                         # 初始化，用于记录当前迭代中，已经计算了多少个样本
        # tqdm是一个进度条显示器，可以在终端打印出现在的训练进度
        train_bar = tqdm(train_loader, file=sys.stdout, ncols=100)
        for data in train_bar :
            images, labels = data 
            sample_num += images.shape[0] #[64, 3, 224, 224]
            optimizer.zero_grad()
            outputs = net(images.to(device)) # output_shape: [batch_size, num_classes]
            pred_class = torch.max(outputs, dim=1)[1] # torch.max 返回值是一个tuple，第一个元素是max值，第二个元素是max值的索引。
            acc_num += torch.eq(pred_class, labels.to(device)).sum() 
            loss = loss_function(outputs, labels.to(device)) # 求损失
            loss.backward() # 自动求导
            optimizer.step() # 梯度下降

            # print statistics 
            train_acc = acc_num.item() / sample_num 
            # .desc是进度条tqdm中的成员变量，作用是描述信息
            train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,  epochs, loss)

        # validate
        net.eval()
        acc_num = 0.0  # accumulate accurate number per epoch
        with torch.no_grad(): 
            for val_data in validate_loader:
                val_images, val_labels = val_data
                outputs = net(val_images.to(device)) 
                predict_y = torch.max(outputs, dim=1)[1] 
                acc_num += torch.eq(predict_y, val_labels.to(device)).sum().item() 

        val_accurate = acc_num / val_num
        print('[epoch %d] train_loss: %.3f  train_acc: %.3f  val_accuracy: %.3f' %  (epoch + 1, loss, train_acc, val_accurate))   
        # 判断当前验证集的准确率是否是最大的，如果是，则更新之前保存的权重
        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), os.path.join(save_path, "AlexNet.pth") )

        # 每次迭代后清空这些指标，重新计算 
        train_acc = 0.0
        val_accurate = 0.0

    print('Finished Training')

 
# if __name__ == '__main__':
#     main()
main()

验证过程

import os
import json

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

from classic_models.alexnet import AlexNet 

def try_gpu(i=0):
    """如果存在，则返回gpu(i)，否则返回cpu()

    Defined in :numref:`sec_use_gpu`"""
    if torch.cuda.device_count() >= i + 1:
        return torch.device(f'cuda:{i}')
    try:
        return torch.device('mps')
    except:
        return torch.device('cpu')

def main():
    device = try_gpu()
    print("using {} device.".format(device))

    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 = "/Users/jiangxiyu/根目录/深度学习/flower/train/daisy/5547758_eea9edfd54_n.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 = '/Users/jiangxiyu/根目录/深度学习/flower/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 = "/Users/jiangxiyu/根目录/深度学习/Deep-Learning-Image-Classification-Models-Based-CNN-or-Attention/results/weights/alexnet/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()

AlexNet 网络结构

import torch.nn as nn
import torch
from torchsummary import summary

class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[96, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[96, 27, 27]

            nn.Conv2d(96, 256, kernel_size=5, padding=2),           # output[256, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[256, 13, 13]

            nn.Conv2d(256, 384, kernel_size=3, padding=1),          # output[384, 13, 13]
            nn.ReLU(inplace=True),

            nn.Conv2d(384, 384, kernel_size=3, padding=1),          # output[384, 13, 13]
            nn.ReLU(inplace=True),

            nn.Conv2d(384, 256, kernel_size=3, padding=1),          # output[256, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[256, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),

            nn.Dropout(p=0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            
            nn.Linear(4096, 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)

def alexnet(num_classes): 
    model = AlexNet(num_classes=num_classes)
    return model

net = AlexNet(num_classes=1000)
summary(net.to('mps'), (3,224,224))
#########################################################################################################################################
# Total params: 62,378,344
# Trainable params: 62,378,344
# Non-trainable params: 0
# ----------------------------------------------------------------
# Input size (MB): 0.57
# Forward/backward pass size (MB): 11.09
# Params size (MB): 237.95
# Estimated Total Size (MB): 249.62
# ----------------------------------------------------------------
# conv_parameters:  3,747,200
# fnn_parameters:  58,631,144   93% 的参数量