该项目用PaddlePaddle训练CNN实现food-11数据集的11类食物分类。先解压含训练、验证、测试集的数据集，制作标签文档，继承Dataset类生成数据集。构建含3个卷积层、池化层等的CNN，用Adam优化器等训练，训练5轮后保存模型，最后测试单张图片，虽准确率不高但跑通流程。
☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜
食物图片分类
项目描述
训练一个简单的卷积神经网络，实现食物图片的分类。
数据集介绍
本次使用的数据集为food-11数据集，共有11类
Bread, Dairy product, Dessert, Egg, Fried food, Meat, Noodles/Pasta, Rice, Seafood, Soup, and Vegetable/Fruit.
（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）
Training set: 9866张
Validation set: 3430张
Testing set: 3347张
数据格式 下载 zip 档后解压缩会有三个资料夹，分别为training、validation 以及 testing
training 以及 validation 中的照片名称格式为 [类别]_[编号].jpg，例如 3_100.jpg 即为类别 3 的照片（编号不重要）
实现方式
paddlepaddle
思路方法
解压数据集
查看数据内容：training、validation 和 testing文件夹
类似于work/food-11/training/0_101.jpg 文件
[类别]_[编号].jpg
I-Shop购物系统下载部分功能简介：商品收藏夹功能热门商品最新商品分级价格功能自选风格打印结算页面内部短信箱商品评论增加上一商品，下一商品功能增强商家提示功能友情链接用户在线统计用户来访统计用户来访信息用户积分功能广告设置用户组分类邮件系统后台实现更新用户数据系统图片设置模板管理CSS风格管理申诉内容过滤功能用户注册过滤特征字符IP库管理及来访限制及管理压缩，恢复，备份数据库功能上传文件管理商品类别管理商品添加/修改/
制作图片和标签文档
继承paddle.io.dataset类生成数据集
创建CNN网络
训练数据
测试数据
说明：
本项目素材和内容源于李宏毅老师课程，但是是使用飞桨实现的！
本项目仅仅是跑通了，对于准确率没有要求和细细琢磨，仅供参考！
In [ ]
# !unzip -d work data/data75768/food-11.zip # 解压缩food-11数据集
In [ ]
import paddleprint(f'当前Paddle版本：{paddle.__version__}')
当前Paddle版本：2.0.1
In [ ]
import osimport paddleimport paddle.vision.transforms as Timport numpy as npfrom PIL import Imageimport paddle.nn.functional as F
In [ ]
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
['testing', 'validation', 'training']
In [ ]
data = '10_alksn'data[0:data.rfind('_', 1)] # 判断_位置并截取下划线前面数据
'10'
In [ ]
# 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)
testing 3347 validation 3430 training 9866
训练集和验证集样式:
测试集:
In [22]
# 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
['/home/aistudio/work/food-11/training/2_1043.jpg', '2']
In [15]
# 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)
In [16]
# 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
train大小： 9866 eval大小： 3430 [[[0.30588236 0.2509804 0.1882353 ... 0.19607843 0.19607843 0.19215687] [0.23921569 0.19607843 0.13725491 ... 0.19607843 0.1882353 0.18039216] [0.02352941 0.01176471 0.00392157 ... 0.19607843 0.18039216 0.1764706 ] ... [0.50980395 0.5137255 0.5176471 ... 0.5372549 0.5372549 0.52156866] [0.5137255 0.5137255 0.5137255 ... 0.5411765 0.53333336 0.5176471 ] [0.5176471 0.5137255 0.50980395 ... 0.52156866 0.5176471 0.5176471 ]] [[0.27058825 0.21568628 0.15294118 ... 0.00392157 0. 0. ] [0.20392157 0.14117648 0.09411765 ... 0.00392157 0. 0. ] [0.01568628 0.00784314 0.00392157 ... 0.00784314 0.00392157 0. ] ... [0.45490196 0.45882353 0.45882353 ... 0.4862745 0.47843137 0.4745098 ] [0.45490196 0.45882353 0.4627451 ... 0.47843137 0.46666667 0.46666667] [0.4509804 0.45490196 0.45882353 ... 0.47058824 0.46666667 0.45882353]] [[0.14509805 0.12156863 0.05098039 ... 0.00392157 0.00784314 0.00392157] [0.06666667 0.04313726 0.01960784 ... 0.00392157 0.00392157 0. ] [0. 0.00784314 0.00784314 ... 0.00784314 0.00392157 0.00392157] ... [0.33333334 0.32941177 0.33333334 ... 0.4 0.40392157 0.40784314] [0.32941177 0.32941177 0.32941177 ... 0.4 0.4 0.3882353 ] [0.3137255 0.33333334 0.3372549 ... 0.39215687 0.39607844 0.38431373]]] (3, 100, 100) 2
卷积神经网络示意图
In [18]
# 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
In [19]
network = MyCNN() # 模型实例化paddle.summary(network, (1,3,100,100)) # 模型结构查看
--------------------------------------------------------------------------- Layer (type) Input Shape Output Shape Param # =========================================================================== Conv2D-1 [[1, 3, 100, 100]] [1, 20, 96, 96] 1,520 MaxPool2D-1 [[1, 20, 96, 96]] [1, 20, 48, 48] 0 BatchNorm2D-1 [[1, 20, 48, 48]] [1, 20, 48, 48] 80 Conv2D-2 [[1, 20, 48, 48]] [1, 50, 44, 44] 25,050 MaxPool2D-2 [[1, 50, 44, 44]] [1, 50, 22, 22] 0 BatchNorm2D-2 [[1, 50, 22, 22]] [1, 50, 22, 22] 200 Conv2D-3 [[1, 50, 22, 22]] [1, 50, 18, 18] 62,550 MaxPool2D-3 [[1, 50, 18, 18]] [1, 50, 9, 9] 0 Linear-1 [[1, 4050]] [1, 218] 883,118 Linear-2 [[1, 218]] [1, 100] 21,900 Linear-3 [[1, 100]] [1, 11] 1,111 =========================================================================== Total params: 995,529 Trainable params: 995,249 Non-trainable params: 280 --------------------------------------------------------------------------- Input size (MB): 0.11 Forward/backward pass size (MB): 3.37 Params size (MB): 3.80 Estimated Total Size (MB): 7.29 ---------------------------------------------------------------------------
{'total_params': 995529, 'trainable_params': 995249}
In [21]
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
The loss value printed in the log is the current step, and the metric is the average value of previous step. Epoch 1/5 step 155/155 [==============================] - loss: 2.5430 - acc: 0.1008 - 473ms/step Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 54/54 [==============================] - loss: 2.5167 - acc: 0.1055 - 557ms/step Eval samples: 3430 Epoch 2/5 step 155/155 [==============================] - loss: 2.4430 - acc: 0.1008 - 473ms/step Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 54/54 [==============================] - loss: 2.5167 - acc: 0.1055 - 559ms/step Eval samples: 3430 Epoch 3/5 step 155/155 [==============================] - loss: 2.4430 - acc: 0.1008 - 475ms/step Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 54/54 [==============================] - loss: 2.5167 - acc: 0.1055 - 558ms/step Eval samples: 3430 Epoch 4/5 step 155/155 [==============================] - loss: 2.5430 - acc: 0.1008 - 474ms/step Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 54/54 [==============================] - loss: 2.5167 - acc: 0.1055 - 560ms/step Eval samples: 3430 Epoch 5/5 step 155/155 [==============================] - loss: 2.4430 - acc: 0.1008 - 474ms/step Eval begin... The loss value printed in the log is the current batch, and the metric is the average value of previous step. step 54/54 [==============================] - loss: 2.5167 - acc: 0.1055 - 557ms/step Eval samples: 3430
In [29]
model.save('finetuning/mnist') # 保存模型
In [26]
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
In [33]
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
预测的结果为: 0
