Deep learning practical basic case - Convolutional neural network (CNN) cat and dog recognition based on Xception | Case 2

Today I use a lightweight network Xception to do a simple cat and dog recognition case. My environment is as follows:

• pytorch：2.0
• python：3.8
• jupyter notebook

1. Environmental preparation

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings

warnings.filterwarnings("ignore")             #忽略警告信息

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

# 输出
device(type='cuda')

2. Data preprocessing

Read data:

import os,PIL,random,pathlib

data_dir = 'dataset/'
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames

# 输出
['cat', 'dog']

data processing

# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    # transforms.RandomHorizontalFlip(), # 随机水平翻转
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

total_data = datasets.ImageFolder(data_dir,transform=train_transforms)
total_data

Classify data sets

total_data.class_to_idx

# 输出
{
    
    'cat': 0, 'dog': 1}

Partition the data set

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset

Dataset loading

batch_size = 4

train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True)

View dataset shape

for X, y in test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

3. Build the model

The specific network structure of Xception is as follows:

import math
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
from torch.nn import init
import torch


class SeparableConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, bias=False):
        super(SeparableConv2d, self).__init__()

        self.conv1 = nn.Conv2d(in_channels, in_channels, kernel_size, stride, padding, dilation, groups=in_channels,
                               bias=bias)
        self.pointwise = nn.Conv2d(in_channels, out_channels, 1, 1, 0, 1, 1, bias=bias)

    def forward(self, x):
        x = self.conv1(x)
        x = self.pointwise(x)
        return x

class Block(nn.Module):
    def __init__(self, in_filters, out_filters, reps, strides=1, start_with_relu=True, grow_first=True):
        # :parm reps:块重复次数
        super(Block, self).__init__()

        # Middle flow无需做这一步，而其余块需要，以做跳连
        # 1)Middle flow输入输出特征图个数始终一致，且Stride恒为1
        # 1）其余快stride=2，这样可以将特征图尺寸减半，获得与最大池化减半特征图尺寸同样的效果
        if out_filters != in_filters or strides != 1:
            self.skip = nn.Conv2d(in_filters, out_filters, 1, stride=strides, bias=False)
            self.skipbn = nn.BatchNorm2d(out_filters)
        else:
            self.skip = None

        self.relu = nn.ReLU(inplace=True)
        rep = []

        filters = in_filters
        if grow_first:
            rep.append(self.relu)
            # 这里的卷积不改变特征图尺寸
            rep.append(SeparableConv2d(in_filters, out_filters, 3, stride=1, padding=1, bias=False))
            rep.append(nn.BatchNorm2d(out_filters))
            filters = out_filters

        for i in range(reps - 1):
            rep.append(self.relu)
            rep.append(SeparableConv2d(filters, filters, 3, stride=1, padding=1, bias=False))
            rep.append(nn.BatchNorm2d(filters))

        if not grow_first:
            rep.append(self.relu)
            rep.append(SeparableConv2d(in_filters, out_filters, 3, stride=1, padding=1, bias=False))
            rep.append(nn.BatchNorm2d(out_filters))

        if not start_with_relu:
            rep = rep[1:]
        else:
            rep[0] = nn.ReLU(inplace=False)

        # Middle flow 的stride恒为1，因此无需做池化，而其余块需要
        # 其余块的stride=2，因此这里的最大池化可以将特征图尺寸减半
        if strides != 1:
            rep.append(nn.MaxPool2d(3, strides, 1))
        self.rep = nn.Sequential(*rep)

    def forward(self, inp):
        x = self.rep(inp)

        if self.skip is not None:
            skip = self.skip(inp)
            skip = self.skipbn(skip)
        else:
            skip = inp

        x += skip
        return x

class Xception(nn.Module):
    def __init__(self, num_classes):
        super(Xception, self).__init__()
        self.num_classes = num_classes # 总分类数

        ###############################定义 Entry flow#################################
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3, stride=2, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(32)
        self.relu = nn.ReLU(inplace=True)

        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(64)
        # do relu here

        # Block中的参数顺序：in_filters,out_filters,reps,stride,start_with_relu,grow_first
        self.block1 = Block(64, 128, 2, 2, start_with_relu=False, grow_first=True)
        self.block2 = Block(128, 256, 2, 2, start_with_relu=True, grow_first=True)
        self.block3 = Block(256, 728, 2, 2, start_with_relu=True, grow_first=True)

        ##############################定义 Middle flow################################
        self.block4 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block5 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block6 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block7 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)

        self.block8 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block9 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block10 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)
        self.block11 = Block(728, 728, 3, 1, start_with_relu=True, grow_first=True)


        #############################定义 Exit flow###################################
        self.block12 = Block(728, 1024, 2, 2, start_with_relu=True, grow_first=False)

        self.conv3 = SeparableConv2d(1024, 1536, 3, 1, 1)
        self.bn3 = nn.BatchNorm2d(1536)


        # do relu here
        self.conv4 = SeparableConv2d(1536, 2048, 3, 1, 1)
        self.bn4 = nn.BatchNorm2d(2048)

        self.fc = nn.Linear(2048, num_classes)

        ###############################################################################




        #--------------------init weights---------------------#
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
        #----------------------------------------------------------------




    def forward(self, x):
        ###########################定义 Entry flow ######################################
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)

        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu(x)

        x = self.block1(x)
        x = self.block2(x)
        x = self.block3(x)

        ######################## 定义 Middle flow#######################################
        x = self.block4(x)
        x = self.block5(x)
        x = self.block6(x)
        x = self.block7(x)
        x = self.block8(x)
        x = self.block9(x)
        x = self.block10(x)
        x = self.block11(x)

        ######################### 定义 Exit flow #######################################
        x = self.block12(x)

        x = self.conv3(x)
        x = self.bn3(x)
        x = self.relu(x)

        x = self.conv4(x)
        x = self.bn4(x)
        x = self.relu(x)

        x = F.adaptive_avg_pool2d(x, (1,1))
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x

4. Instantiation model

device = "cuda:0" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

xception = Xception(num_classes = 2)
model = xception.to(device)
model

5. Training model

5.1 Build training function

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小
    num_batches = len(dataloader)   # 批次数目, (size/batch_size，向上取整)

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率

    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失

        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新

        # 记录acc与loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

5.2 Building test functions

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小
    num_batches = len(dataloader)          # 批次数目, (size/batch_size，向上取整)
    test_loss, test_acc = 0, 0

    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)

            # 计算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)

            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

5.3 Start formal training

import copy

optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-3)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数

epochs     = 5

train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

best_acc = 0    # 设置一个最佳准确率，作为最佳模型的判别指标

for epoch in range(epochs):

    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)

    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

    # 保存最佳模型到 best_model
    if epoch_test_acc > best_acc:
        best_acc   = epoch_test_acc
        best_model = copy.deepcopy(model)

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)

    # 获取当前的学习率
    lr = optimizer.state_dict()['param_groups'][0]['lr']

    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss,
                          epoch_test_acc*100, epoch_test_loss, lr))

# 保存最佳模型到文件中
PATH = './best_model.pth'  # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)

print('Done')

6. Visualization accuracy and loss

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率

epochs_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

7. Individual prediction

Just go online and find a picture of a cat or dog and make a prediction.

# 预测

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

plt.rcParams['font.sans-serif']=['SimHei']  #解决中文显示乱码问题
plt.rcParams['axes.unicode_minus']=False  #解决坐标轴负数的负号显示问题



data_transform = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])


img = Image.open("cat.jpg")
plt.imshow(img)
img = data_transform(img)
img = torch.unsqueeze(img, dim=0)
name=['狗','猫']
model_weight_path = "best_model.pth"
model = Xception(num_classes = 2)
model.load_state_dict(torch.load(model_weight_path))
model.eval()
with torch.no_grad():
    output = torch.squeeze(model(img))

    predict = torch.softmax(output, dim=0)
    # 获得最大可能性索引
    predict_cla = torch.argmax(predict).numpy()
    print('索引为', predict_cla)
print('预测结果为：{},置信度为: {}'.format(name[predict_cla], predict[predict_cla].item()))
plt.show()

Summarize

• Xception (also known as Extreme Inception) is a convolutional neural network architecture proposed by Google in 2016. Its name is composed of the words 'Extreme' and 'Inception'. Xception is improved based on the Inception V3 model and uses depthwise separable convolution instead of traditional convolution, thereby more effectively reducing the number of parameters and computational complexity of the model.
• In the traditional Inception model, each computing unit uses two convolutional layers. A 1x1 convolutional layer is used to reduce the number of channels of the feature map, followed by a 3x3 convolutional layer for feature extraction. Xception separates 1x1 and 3x3 convolutions one after another, and uses depth-separable convolutions as the basic calculation unit. Depthwise separable convolution decomposes the standard convolution into two parts. First, it uses depth convolution to process each input channel, and then uses 1x1 point-wise convolution to fuse the channels, thereby obtaining a feature extraction effect similar to that of standard convolution. . Compared with standard convolution, depth-separable convolution can significantly reduce the amount of parameters and training calculations.
• After using depth-separable convolution units to replace traditional convolution operations, the Xception model has greatly improved its computational efficiency and model size compared to Inception V3.
• In short, the advantage of the Xception model is that it can maintain excellent performance while greatly reducing the amount of network parameters and computational complexity. Therefore, the Xception model has been widely used in tasks such as image classification and target detection.