paddle实现食物分类

# !unzip -d work data/data75768/food-11.zip # 解压缩food-11数据集

import paddleprint(f'当前Paddle版本：{paddle.__version__}')

import osimport paddleimport paddle.vision.transforms as Timport numpy as npfrom PIL import Imageimport paddle.nn.functional as F

data_path = '/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character_folders

data = '10_alksn'data[0:data.rfind('_', 1)]   # 判断_位置并截取下划线前面数据

# 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':  # 检查是否是训练集
            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)  # 输出文件夹及图片数量
        else:            for img in character_imgs:
                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)

# 测验下面类中__init__输出内容with open(f'training_set.txt') as f:  # 查看文件内容
    for line in f.readlines():  # 逐行读取
        info = line.strip().split('\t')  # 以\t为切换符生成列表
        # print(info)
        if len(info) > 0:  # 列表不为空
            print([info[0].strip(), info[1].strip()])  # 输出内容
        break

# 继承paddle.io.Dataset对数据集做处理class FoodDataset(paddle.io.Dataset):
    """
    数据集类的定义（注释见上方）
    """
    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)  # 读取图片
        img = img.resize((100, 100), Image.ANTIALIAS)  # 图片大小样式归一化
        img = np.array(img).astype('float32')  # 转换成数组类型浮点型32位
        img = img.transpose((2, 0, 1))     #读出来的图像是rgb,rgb,rbg..., 转置为 rrr...,ggg...,bbb...
        img = img/255.0  # 数据缩放到0-1的范围
        return img, np.array(label, dtype='int64')    def __len__(self):
        """
        获取样本总数
        """
        return len(self.data)

# 训练的数据提供器train_dataset = FoodDataset(mode='training')# 测试的数据提供器eval_dataset = FoodDataset(mode='validation')# 查看训练和测试数据的大小print('train大小：', train_dataset.__len__())print('eval大小：', eval_dataset.__len__())# 查看图片数据、大小及标签for data, label in train_dataset:    print(data)    print(np.array(data).shape)    print(label)    break

# 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)  # 二维卷积层
        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):
        # 将输入数据的样子该变成[1,3,100,100]
        input = paddle.reshape(input,shape=[-1,3,100,100])  # 转换维读
        # print(input.shape)
        x = self.conv0(input)  #数据输入卷积层
        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 y

network = MyCNN()  # 模型实例化paddle.summary(network, (1,3,100,100))  # 模型结构查看

model = paddle.Model(network)  # 模型封装# 配置优化器、损失函数、评估指标model.prepare(paddle.optimizer.Adam(learning_rate=0.0001, parameters=model.parameters()), 
              paddle.nn.CrossEntropyLoss(), 
              paddle.metric.Accuracy())# 训练可视化VisualDL工具的回调函数visualdl = paddle.callbacks.VisualDL(log_dir='visualdl_log')   

# 启动模型全流程训练model.fit(train_dataset,  # 训练数据集
          eval_dataset,   # 评估数据集
          epochs=5,       # 训练的总轮次
          batch_size=64,  # 训练使用的批大小
          verbose=1,      # 日志展示形式
          callbacks=[visualdl])  # 设置可视化

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

def openimg():  # 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 = img.resize((100, 100), Image.ANTIALIAS)  # 大小归一化
            img = np.array(img).astype('float32')  # 转换成 数组
            img = img.transpose((2, 0, 1))     #读出来的图像是rgb,rgb,rbg..., 转置为 rrr...,ggg...,bbb...
            img = img/255.0  # 缩放
            txt.append(line[:-1])  # 生成列表
            test_img.append(img)  
        return txt,test_img
img_path, img = openimg()  # 读取列表

from PIL import Image
site = 255  # 读取图片位置model_state_dict = paddle.load('finetuning/mnist.pdparams')  # 读取模型model = MyCNN()  # 实例化模型model.set_state_dict(model_state_dict) 
model.eval()

ceshi = model(paddle.to_tensor(img[site]))  # 测试print('预测的结果为:', np.argmax(ceshi.numpy()))  # 获取值Image.open(img_path[site])  # 显示图片