基于CNN的图像分类任务

---

前言

使用的百度的paddle框架，在AIstudio上面运行本次任务。

# 查看当前挂载的数据集目录, 该目录下的变更重启环境后会自动还原
# View dataset directory. 
# This directory will be recovered automatically after resetting environment. 
!ls /home/aistudio/data
# 查看工作区文件, 该目录下的变更将会持久保存. 请及时清理不必要的文件, 避免加载过慢.
# View personal work directory. 
# All changes under this directory will be kept even after reset. 
# Please clean unnecessary files in time to speed up environment loading. 
!ls /home/aistudio/work
# 如果需要进行持久化安装, 需要使用持久化路径, 如下方代码示例:
# If a persistence installation is required, 
# you need to use the persistence path as the following: 
!mkdir /home/aistudio/external-libraries
!pip install beautifulsoup4 -t /home/aistudio/external-libraries
# 同时添加如下代码, 这样每次环境(kernel)启动的时候只要运行下方代码即可: 
# Also add the following code, 
# so that every time the environment (kernel) starts, 
# just run the following code: 
import sys 
sys.path.append('/home/aistudio/external-libraries')
#解压数据集
!unzip -d work data/data78873/food-11.zip
!rm -rf work/__MACOSX

---

一、导入相关的库

#导入相关库
import os
import paddle
import paddle.vision.transforms as T
import numpy as np
from PIL import Image
import paddle
import paddle.nn.functional as F
import cv2
from sklearn.utils import shuffle

二、数据读取

# 读取数据
data_path='work/home/aistudio/work/food-11'# 设置初始文件地址
character_folders=os.listdir(data_path)# 查看地址下文件夹

# 每次运行前删除txt，重新新建标签列表
if(os.path.exists('./training_set.txt')):# 判断有误文件
    os.remove('./training_set.txt')# 删除文件
if(os.path.exists('./validation_set.txt')):
    os.remove('./validation_set.txt')
if(os.path.exists('./testing_set.txt')):
    os.remove('./testing_set.txt')

for character_folder in character_folders: #循环文件夹列表
    with open(f'./{character_folder}_set.txt', 'a') as f_train:# 新建文档以追加的形式写入
        character_imgs = os.listdir(os.path.join(data_path,character_folder))# 读取文件夹下面的内容
        count = 0
        if character_folder in 'testing':# 检查是否是测试集
            for img in character_imgs:# 循环列表
                f_train.write(os.path.join(data_path,character_folder,img) + '\n')# 把地址写入文档
                count += 1
            print(character_folder,count)
        else:
            for img in character_imgs:# 检查是否是训练集和测试集
                f_train.write(os.path.join(data_path,character_folder,img) + '\t' + img[0:img.rfind('_', 1)] + '\n')# 写入地址及标签
                count += 1
            print(character_folder,count)

三、数据预处理

下面使用paddle.vision.transforms.Compose做数据预处理，主要是这几个部分：
1、以RGB格式加载图片
2、将图片resize，从224x224变成100x100
3、进行transpose操作，从HWC格式转变成CHW格式
4、将图片的所有像素值进行除以255进行归一化
5、对各通道进行减均值、除标准差

img_h, img_w = 100, 100 #适当调整，影响不大
means, stdevs = [], []
img_list = []

imgs_path = 'work/home/aistudio/work/food-11/training'
imgs_path_list = os.listdir(imgs_path)

len_ = len(imgs_path_list)
i = 0
for item in imgs_path_list:
    img = cv2.imread(os.path.join(imgs_path,item))
    img = cv2.resize(img,(img_w,img_h))
    img = img[:, :, :, np.newaxis]
    img_list.append(img)
    i += 1
    # print(i,'/',len_)

imgs_path = 'work/home/aistudio/work/food-11/testing'
imgs_path_list = os.listdir(imgs_path)

len_ = len(imgs_path_list)
i = 0
for item in imgs_path_list:
    img = cv2.imread(os.path.join(imgs_path,item))
    img = cv2.resize(img,(img_w,img_h))
    img = img[:, :, :, np.newaxis]
    img_list.append(img)
    i += 1

imgs=np.concatenate(img_list,axis=3)
imgs=imgs.astype(np.float32)/255.

for i in range(3):
    pixels=imgs[:, :, i, :].ravel()  # 拉成一行
    means.append(np.mean(pixels))
    stdevs.append(np.std(pixels))

# BGR --> RGB ， CV读取的需要转换，PIL读取的不用转换
means.reverse()
stdevs.reverse()

print("normMean = {}".format(means))
print("normStd = {}".format(stdevs))

# 只需要执行一次代码记录住数据即可
# normMean = [0.5560434, 0.4515875, 0.34473255]
# normStd = [0.27080873, 0.2738704, 0.280732]

normMean=[0.5560434,0.4515875,0.34473255]
normStd=[0.27080873,0.2738704,0.280732]

# 定义数据预处理
data_transforms = T.Compose([
    T.Resize(size=(100,100)),
    T.RandomHorizontalFlip(100),
    T.RandomVerticalFlip(100),
    T.RandomRotation(90),
    T.CenterCrop(100),
    T.Transpose(),# HWC -> CHW
    T.Normalize(
        mean=[0.5560434,0.4515875,0.34473255],#归一化 上个模块所求的均值与标准差 
        std=[0.27080873,0.2738704,0.280732],
        to_rgb=True)
        #计算过程：output[channel] = (input[channel] - mean[channel]) / std[channel]
])

四、继承dataset类

#继承dataset类
class FoodDataset(paddle.io.Dataset):
    """
    数据集类的定义
    """
    def __init__(self, mode='training_set'):
        """
        初始化函数
        """
        self.data = []
        with open(f'{mode}_set.txt') as f:
            for line in f.readlines():
                info = line.strip().split('\t')
                if len(info) > 0:
                    self.data.append([info[0].strip(), info[1].strip()])
    

    def __getitem__(self, index ):
        """
        读取图片，对图片进行归一化处理，返回图片和标签
        """
        image_file, label = self.data[index]   # 获取数据
        img = Image.open(image_file).convert('RGB')    # 读取图片

        return data_transforms(img).astype('float32'),np.array(label, dtype='int64')
    
    def __len__(self):
        return len(self.data)

train_dataset = FoodDataset(mode='training')
train_loader = paddle.io.DataLoader(train_dataset, places=paddle.CPUPlace(), batch_size=64, shuffle=True, num_workers=0)
eval_dataset = FoodDataset(mode='training')
val_loader = paddle.io.DataLoader(eval_dataset, places=paddle.CPUPlace(), batch_size=64,shuffle=True, num_workers=0)

#查看训练和验证集数据的大小
print('train size:', train_dataset.__len__())
print('eval size:', eval_dataset.__len__())

五、搭建模型

# 继承paddle.nn.Layer类，用于搭建模型
class MyCNN(paddle.nn.Layer) :
    def __init__(self):
        super(MyCNN,self).__init__()
        self.conv0 = paddle.nn.Conv2D(in_channels=3,out_channels=20,kernel_size=5,padding = 0)
        self.pool0 = paddle.nn.MaxPool2D(kernel_size =2, stride =2)#最大池化层
        self._batch_norm_0 = paddle.nn.BatchNorm2D(num_features = 20)#归一层

        self.conv1 = paddle.nn.Conv2D(in_channels=20,out_channels=50,kernel_size=5,padding=0)
        self.pool1 = paddle.nn.MaxPool2D(kernel_size=2,stride = 2)
        self._batch_norm_1 = paddle.nn.BatchNorm2D(num_features = 50)

        self.conv2 = paddle.nn.Conv2D(in_channels=50,out_channels=50,kernel_size=5,padding=0)
        self.pool2 = paddle.nn.MaxPool2D(kernel_size =2,stride = 2)
        self.fc1= paddle.nn.Linear(in_features=4050,out_features=218)# 线性层
        self.fc2 = paddle.nn.Linear(in_features=218,out_features=100)
        self.fc3 = paddle.nn.Linear(in_features=100,out_features=11)

    def forward(self,input):
        #将输入教据的样子该变成[ 1,3,180,100]
        input = paddle.reshape(input,shape=[-1,3,100,100]) #转换维读
        # print(input.shape)
        x = self.conv0( input)#教据输入卷积层
        x = F.relu(x)#激活层
        x = self.pool0(x)#池化层
        x = self._batch_norm_0(x)#归一层

        x = self.conv1(x)
        x = F.relu(x)
        x = self.pool1(x)
        x = self._batch_norm_1(x)

        x = self.conv2(x)
        x = F.relu(x)
        x = self.pool2(x)
        x = paddle.reshape(x,[x.shape[0],-1])
        # print(x.shape)

        x = self.fc1(x)#线性层
        x = F.relu(x)
        x = self.fc2(x)
        x = F.relu(x)
        x = self.fc3(x)
        #y = F.softmax(x)# 分类器
        return x

network = MyCNN()  # 模型实例化

六、训练模型

# 训练模型
# 实例化模型
inputs = paddle.static.InputSpec(shape=[None, 3, 100, 100], name='inputs')
labels = paddle.static.InputSpec(shape=[None, 11], name='labels')
model = paddle.Model(network,inputs,labels)

# 模型训练相关配置，准备损失计算方法，优化器和精度计算方法
# 定义优化器
scheduler = paddle.optimizer.lr.LinearWarmup(
        learning_rate=0.001, warmup_steps=100, start_lr=0, end_lr=0.001, verbose=True)
optim = paddle.optimizer.SGD(learning_rate=scheduler, parameters=model.parameters())

# 配置模型
model.prepare(
    optim,
    paddle.nn.CrossEntropyLoss(),
    paddle.metric.Accuracy()   
    )
visualdl = paddle.callbacks.VisualDL(log_dir='visualdl_log')
# 模型训练与评估
model.fit(
        train_loader,    # 训练数据集
        val_loader,      # 评估数据集
        epochs=1,        # 训练的总轮次
        batch_size=128,  # 训练使用的批大小
        verbose=1,       # 日志展示形式
        callbacks=[visualdl])  # 设置可视化 

# 模型评估
model.evaluate(eval_dataset, batch_size=128, verbose=1)

七、保存模型

#保存模型
model.save('finetuning/food') # 保存模型

八、测试

# 测试
def opening():  # 读取图片函数
    with open(f'testing_set.txt') as f:  # 读取文件夹
        test_img = []
        txt = []
        for line in f.readlines():  # 循环读取每一行
            img = Image.open(line[:-1])  # 打开图片
            img = data_transforms(img).astype('float32')
            txt.append(line[:-1])  # 生成列表
            test_img.append(img)
        return txt,test_img
img_path, img = opening()  # 读取列表

from PIL import Image
model_state_dict = paddle.load('finetuning/food.pdparams')  # 读取模型
model = MyCNN()  # 实例化模型
model.set_state_dict(model_state_dict)
model.eval()

site = 20  # 读取图片位置

ceshi = model(paddle.to_tensor(img[site]))  # 测试
print('预测的结果为：',np.argmax(ceshi.numpy()))  # 获取值
value = ["面包","乳制品","甜点","鸡蛋","油炸食品","肉类","面条/意大利面","米饭","海鲜","汤","蔬菜/水果"]
print('        ', value[np.argmax(ceshi.numpy())])
Image.open(img_path[site])  # 显示图片

九、结果

写在最后

仅对个人的深度学习实验做一次记录，文中不足、错误之处欢迎指正；
创作不易，点个赞吧！