本项目基于飞桨2.0，使用food-11数据集（含11类食品，共16643张图片）训练分类模型。通过搭建简单cnn，经数据预处理（求均值标准差、归一化等）、调整训练参数优化，最终在验证集达到50%-55%正确率，实现对面包、肉类等11类食品的分类，并完成模型保存与测试展示。
☞☞☞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☜☜☜
基于飞桨2.0的食品图片分类实战应用
项目描述
本项目使用的是李宏毅机器学习中作业三的数据集
包含（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）十一类的食品数据，对其进行训练分类
搭建训练一个简单的卷积神经网络，实现这十一类食物图片的分类
项目的优化
1.对各通道进行求均值和标准差
2.更改训练参数
课程链接
课程链接：https://aistudio.baidu.com/aistudio/course/introduce/1978
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）
In [ ]
!unzip -d work data/data76472/food-11.zip # 解压缩food-11数据集
In [ ]
!rm -rf work/__MACOSX
第一步 必要的库引入，数据读取
- 读取数据，新建路径+标签的txt的三个文件
- 核实数据量与题目所给是否相同
In [1]
import osimport paddleimport paddle.vision.transforms as Timport numpy as npfrom PIL import Imageimport paddleimport paddle.nn.functional as Ffrom sklearn.utils import shuffle#在python中运行代码经常会遇到的情况是——代码可以正常运行但是会提示警告，有时特别讨厌。#那么如何来控制警告输出呢？其实很简单，python通过调用warnings模块中定义的warn()函数来发出警告。我们可以通过警告过滤器进行控制是否发出警告消息。import warnings
warnings.filterwarnings("ignore")
data_path = '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)
testing 3347 training 9866 validation 3430
第二步 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：
- 以RGB格式加载图片
- 将图片resize，从224x224变成100x100
- 进行transpose操作，从HWC格式转变成CHW格式
- 将图片的所有像素值进行除以255进行归一化
- 对各通道进行减均值、除标准差
In [2]
# 只有第一次需要执行 一次需要一分钟多import numpy as npimport cv2import os
img_h, img_w = 100, 100 #适当调整，影响不大means, stdevs = [], []
img_list = []
imgs_path = 'work/food-11/training'imgs_path_list = os.listdir(imgs_path)
len_ = len(imgs_path_list)
i = 0for 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/food-11/testing'imgs_path_list = os.listdir(imgs_path)
len_ = len(imgs_path_list)
i = 0for 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 += 1imgs = 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]
In [3]
# 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]])
第三步 继承paddle.io.Dataset对数据集做处理
对数据集进行处理
In [4]
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):
"""
获取样本总数
"""
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='validation')
val_loader = paddle.io.DataLoader(train_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__())
train size： 9866 eval size： 3430
第四步 自行搭建CNN神经网络
In [5]
# 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 x
In [6]
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}
第五步 模型配置以及训练
运行时长: 3小时22分钟19秒5毫秒
In [7]
# 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=100, # 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)#已运行，结果太长，已经删除，数据在下图显示
多次运行，在验证集正确率达到0.50-0.55之间
第六步 保存模型
In [8]
model.save('finetuning/mnist') # 保存模型
第七步 测试集案例展示
In [9]
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/mnist.pdparams') # 读取模型model = MyCNN() # 实例化模型model.set_state_dict(model_state_dict)
model.eval()
In [14]
site = 10 # 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
预测的结果为: 9
汤
<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=384x512 at 0x7F3BE0539C10>
