神经网络：基于多层全连接神经网络的宝石分类任务

任务：定义改网络模型，其中包括网络层数及每一层神经元个数，查看验证集上的准确率。

一、导入必要的包

import os
import zipfile
import random
import json
import cv2
import numpy as np
from PIL import Image
import paddle
import matplotlib.pyplot as plt
from paddle.io import Dataset

二、配置参数

train_parameters = {
    "input_size": [3, 224, 224],                           #输入图片的shape
    "class_dim": -1,                                     #分类数
    "src_path":"data/data55032/archive_train.zip",       #原始数据集路径
    "target_path":"/home/aistudio/data/dataset",        #要解压的路径 
    "train_list_path": "./train.txt",              #train_data.txt路径
    "eval_list_path": "./eval.txt",                  #eval_data.txt路径
    "label_dict":{},                                    #标签字典
    "readme_path": "/home/aistudio/data/readme.json",   #readme.json路径
    "num_epochs": 40,                                    #训练轮数
    "train_batch_size": 32,                             #批次的大小
    "learning_strategy": {                              #优化函数相关的配置
        "lr": 0.001                                     #超参数学习率
    } 
}

三、解压数据集

def unzip_data(src_path,target_path):

    if(not os.path.isdir(target_path)):    
        z = zipfile.ZipFile(src_path, 'r')
        z.extractall(path=target_path)
        z.close()
    else:
        print("文件已解压")

四、生成数据列表

def get_data_list(target_path,train_list_path,eval_list_path):
    '''
    生成数据列表
    '''
    #存放所有类别的信息
    class_detail = []
    #获取所有类别保存的文件夹名称
    data_list_path=target_path
    class_dirs = os.listdir(data_list_path)
    if '__MACOSX' in class_dirs:
        class_dirs.remove('__MACOSX')
    # #总的图像数量
    all_class_images = 0
    # #存放类别标签
    class_label=0
    # #存放类别数目
    class_dim = 0
    # #存储要写进eval.txt和train.txt中的内容
    trainer_list=[]
    eval_list=[]
    #读取每个类别
    for class_dir in class_dirs:
        if class_dir != ".DS_Store":
            class_dim += 1
            #每个类别的信息
            class_detail_list = {}
            eval_sum = 0
            trainer_sum = 0
            #统计每个类别有多少张图片
            class_sum = 0
            #获取类别路径 
            path = os.path.join(data_list_path,class_dir)
            # 获取所有图片
            img_paths = os.listdir(path)
            for img_path in img_paths:                                  # 遍历文件夹下的每个图片
                if img_path =='.DS_Store':
                    continue
                name_path = os.path.join(path,img_path)                       # 每张图片的路径
                if class_sum % 15 == 0:                                 # 每10张图片取一个做验证数据
                    eval_sum += 1                                       # eval_sum为测试数据的数目
                    eval_list.append(name_path + "\t%d" % class_label + "\n")
                else:
                    trainer_sum += 1 
                    trainer_list.append(name_path + "\t%d" % class_label + "\n")#trainer_sum测试数据的数目
                class_sum += 1                                          #每类图片的数目
                all_class_images += 1                                   #所有类图片的数目
            
            # 说明的json文件的class_detail数据
            class_detail_list['class_name'] = class_dir             #类别名称
            class_detail_list['class_label'] = class_label          #类别标签
            class_detail_list['class_eval_images'] = eval_sum       #该类数据的测试集数目
            class_detail_list['class_trainer_images'] = trainer_sum #该类数据的训练集数目
            class_detail.append(class_detail_list)  
            #初始化标签列表
            train_parameters['label_dict'][str(class_label)] = class_dir
            class_label += 1
            
    #初始化分类数
    train_parameters['class_dim'] = class_dim
    print(train_parameters)
    #乱序  
    random.shuffle(eval_list)
    with open(eval_list_path, 'a') as f:
        for eval_image in eval_list:
            f.write(eval_image) 
    #乱序        
    random.shuffle(trainer_list) 
    with open(train_list_path, 'a') as f2:
        for train_image in trainer_list:
            f2.write(train_image) 

    # 说明的json文件信息
    readjson = {}
    readjson['all_class_name'] = data_list_path                  #文件父目录
    readjson['all_class_images'] = all_class_images
    readjson['class_detail'] = class_detail
    jsons = json.dumps(readjson, sort_keys=True, indent=4, separators=(',', ': '))
    with open(train_parameters['readme_path'],'w') as f:
        f.write(jsons)
    print ('生成数据列表完成！')

五、初始化

src_path=train_parameters['src_path']
target_path=train_parameters['target_path']
train_list_path=train_parameters['train_list_path']
eval_list_path=train_parameters['eval_list_path']
batch_size=train_parameters['train_batch_size']
'''
解压原始数据到指定路径
'''
unzip_data(src_path,target_path)

'''
划分训练集与验证集，乱序，生成数据列表
'''
#每次生成数据列表前，首先清空train.txt和eval.txt
with open(train_list_path, 'w') as f: 
    f.seek(0)
    f.truncate() 
with open(eval_list_path, 'w') as f: 
    f.seek(0)
    f.truncate() 
    
#生成数据列表   
get_data_list(target_path,train_list_path,eval_list_path)
class Reader(Dataset):
    def __init__(self, data_path, mode='train'):
        """
        数据读取器
        :param data_path: 数据集所在路径
        :param mode: train or eval
        """
        super().__init__()
        self.data_path = data_path
        self.img_paths = []
        self.labels = []

        if mode == 'train':
            with open(os.path.join(self.data_path, "train.txt"), "r", encoding="utf-8") as f:
                self.info = f.readlines()
            for img_info in self.info:
                img_path, label = img_info.strip().split('\t')
                self.img_paths.append(img_path)
                self.labels.append(int(label))

        else:
            with open(os.path.join(self.data_path, "eval.txt"), "r", encoding="utf-8") as f:
                self.info = f.readlines()
            for img_info in self.info:
                img_path, label = img_info.strip().split('\t')
                self.img_paths.append(img_path)
                self.labels.append(int(label))


    def __getitem__(self, index):
        """
        获取一组数据
        :param index: 文件索引号
        :return:
        """
        # 第一步打开图像文件并获取label值
        img_path = self.img_paths[index]
        img = Image.open(img_path)
        if img.mode != 'RGB':
            img = img.convert('RGB') 
        img = img.resize((224, 224), Image.BILINEAR)
        img = np.array(img).astype('float32')
        img = img.transpose((2, 0, 1)) / 255
        label = self.labels[index]
        label = np.array([label], dtype="int64")
        return img, label

    def print_sample(self, index: int = 0):
        print("文件名", self.img_paths[index], "\t标签值", self.labels[index])

    def __len__(self):
        return len(self.img_paths)
train_dataset = Reader('/home/aistudio/',mode='train')

eval_dataset = Reader('/home/aistudio/',mode='eval')

#训练数据加载
train_loader = paddle.io.DataLoader(train_dataset, batch_size=16, shuffle=True)
#测试数据加载
eval_loader = paddle.io.DataLoader(eval_dataset, batch_size = 8, shuffle=False)
train_dataset.print_sample(200)
print(train_dataset.__len__())
eval_dataset.print_sample(0)
print(eval_dataset.__len__())
print(eval_dataset.__getitem__(10)[0].shape)
print(eval_dataset.__getitem__(10)[1].shape)
Batch=0
Batchs=[]
all_train_accs=[]
def draw_train_acc(Batchs, train_accs):
    title="training accs"
    plt.title(title, fontsize=24)
    plt.xlabel("batch", fontsize=14)
    plt.ylabel("acc", fontsize=14)
    plt.plot(Batchs, train_accs, color='green', label='training accs')
    plt.legend()
    plt.grid()
    plt.show()

all_train_loss=[]
def draw_train_loss(Batchs, train_loss):
    title="training loss"
    plt.title(title, fontsize=24)
    plt.xlabel("batch", fontsize=14)
    plt.ylabel("loss", fontsize=14)
    plt.plot(Batchs, train_loss, color='red', label='training loss')
    plt.legend()
    plt.grid()
    plt.show()

六、定义DNN网络模型

class MyDNN(paddle.nn.Layer):
    def __init__(self):
        super(MyDNN,self).__init__()
        self.linear1 = paddle.nn.Linear(in_features=3*224*224, out_features=1024)
        self.relu1 = paddle.nn.ReLU()

        self.linear2 = paddle.nn.Linear(in_features=1024, out_features=512)
        self.relu2 = paddle.nn.ReLU()

        self.linear3 = paddle.nn.Linear(in_features=512, out_features=256)
        self.relu3 = paddle.nn.ReLU()

        self.linear4 = paddle.nn.Linear(in_features=256, out_features=25)

    def forward(self,input):        # forward 定义执行实际运行时网络的执行逻辑
        # input.shape (16, 3, 224, 224)
        x = paddle.reshape(input, shape=[-1,3*224*224]) #-1 表示这个维度的值是从x的元素总数和剩余维度推断出来的，有且只能有一个维度设置为-1
        # print(x.shape)
        x = self.linear1(x)
        x = self.relu1(x)
        # print('1', x.shape)
        x = self.linear2(x)
        x = self.relu2(x)
        # print('2',x.shape)
        x = self.linear3(x)
        x = self.relu3(x)
        # print('3',x.shape)
        y = self.linear4(x)
        # print('4',y.shape)
        return y

七、模型训练

model=MyDNN() #模型实例化
model.train() #训练模式
cross_entropy = paddle.nn.CrossEntropyLoss()
opt=paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters())

epochs_num=train_parameters['num_epochs'] #迭代次数
for pass_num in range(train_parameters['num_epochs']):
    for batch_id,data in enumerate(train_loader()):
        image = data[0]
        label = data[1]

        predict=model(image) #数据传入model

        loss=cross_entropy(predict,label)
        acc=paddle.metric.accuracy(predict,label)#计算精度
        
        if batch_id!=0 and batch_id%5==0:
            Batch = Batch+5 
            Batchs.append(Batch)
            all_train_loss.append(loss.numpy()[0])
            all_train_accs.append(acc.numpy()[0])
            
            print("train_pass:{},batch_id:{},train_loss:{},train_acc:{}".format(pass_num,batch_id,loss.numpy(),acc.numpy()))
        
        loss.backward()       
        opt.step()
        opt.clear_grad()   #opt.clear_grad()来重置梯度

paddle.save(model.state_dict(),'MyDNN')#保存模型

draw_train_acc(Batchs,all_train_accs)
draw_train_loss(Batchs,all_train_loss)

训练结果：

 八、模型评估

para_state_dict = paddle.load("MyDNN")
model = MyDNN()
model.set_state_dict(para_state_dict) #加载模型参数
model.eval() #验证模式

accs = []

for batch_id,data in enumerate(eval_loader()):#测试集
    image=data[0]
    label=data[1]     
    predict=model(image)       
    acc=paddle.metric.accuracy(predict,label)
    accs.append(acc.numpy()[0])
    avg_acc = np.mean(accs)
print("当前模型在验证集上的准确率为:",avg_acc)

准确率为：