项目说明，本项目是李宏毅老师在飞桨授权课程的作业解析
课程 传送门
该项目AiStudio项目 传送门
数据集 传送门
本项目仅用于参考，提供思路和想法并非标准答案！请谨慎抄袭！
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 - 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！
# !unzip -d work data/data75768/food-11.zip # 解压缩food-11数据集
import paddle print(f'当前Paddle版本：{paddle.__version__}')
当前Paddle版本：2.0.1
import os import paddle import paddle.vision.transforms as T import numpy as np from PIL import Image import paddle.nn.functional as F
读取文件
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']
data = '10_alksn' data[0:data.rfind('_', 1)] # 判断_位置并截取下划线前面数据
'10'
# 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
# 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']
# 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
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
# 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
--------------------------------------------------------------------------- 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}
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
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
预测的结果为: 0
传说中的飞桨社区最菜代码人，让我们一起努力！
记住：三岁出品必是精品 （不要脸系列）
