keras实现VGG16 CIFAR10数据集方式


Posted in Python onJuly 07, 2020

我就废话不多说了,大家还是直接看代码吧!

import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, BatchNormalization
from keras import optimizers
import numpy as np
from keras.layers.core import Lambda
from keras import backend as K
from keras.optimizers import SGD
from keras import regularizers
 
#import data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)
 
weight_decay = 0.0005
nb_epoch=100
batch_size=32
 
#layer1 32*32*3
model = Sequential()
model.add(Conv2D(64, (3, 3), padding='same',
input_shape=(32,32,3),kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.3))
#layer2 32*32*64
model.add(Conv2D(64, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
#layer3 16*16*64
model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer4 16*16*128
model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
#layer5 8*8*128
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer6 8*8*256
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer7 8*8*256
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
#layer8 4*4*256
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer9 4*4*512
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer10 4*4*512
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
#layer11 2*2*512
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer12 2*2*512
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
#layer13 2*2*512
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
#layer14 1*1*512
model.add(Flatten())
model.add(Dense(512,kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
#layer15 512
model.add(Dense(512,kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
#layer16 512
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
# 10
 
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=['accuracy'])
 
model.fit(x_train,y_train,epochs=nb_epoch, batch_size=batch_size,
       validation_split=0.1, verbose=1)

补充知识:pytorch一步一步在VGG16上训练自己的数据集

准备数据集及加载,ImageFolder

在很多机器学习或者深度学习的任务中,往往我们要提供自己的图片。也就是说我们的数据集不是预先处理好的,像mnist,cifar10等它已经给你处理好了,更多的是原始的图片。比如我们以猫狗分类为例。在data文件下,有两个分别为train和val的文件夹。然后train下是cat和dog两个文件夹,里面存的是自己的图片数据,val文件夹同train。这样我们的数据集就准备好了。

keras实现VGG16 CIFAR10数据集方式

ImageFolder能够以目录名作为标签来对数据集做划分,下面是pytorch中文文档中关于ImageFolder的介绍:

keras实现VGG16 CIFAR10数据集方式

#对训练集做一个变换
train_transforms = transforms.Compose([
  transforms.RandomResizedCrop(224), #对图片尺寸做一个缩放切割
  transforms.RandomHorizontalFlip(), #水平翻转
  transforms.ToTensor(),   #转化为张量
  transforms.Normalize((.5, .5, .5), (.5, .5, .5)) #进行归一化
])
#对测试集做变换
val_transforms = transforms.Compose([
  transforms.Resize(256),
  transforms.RandomResizedCrop(224),
  transforms.ToTensor(),
  transforms.Normalize((.5, .5, .5), (.5, .5, .5))
])

train_dir = "G:/data/train"      #训练集路径
#定义数据集
train_datasets = datasets.ImageFolder(train_dir, transform=train_transforms)
#加载数据集
train_dataloader = torch.utils.data.DataLoader(train_datasets, batch_size=batch_size, shuffle=True)

val_dir = "G:/datat/val" 
val_datasets = datasets.ImageFolder(val_dir, transform=val_transforms)
val_dataloader = torch.utils.data.DataLoader(val_datasets, batch_size=batch_size, shuffle=True)

迁移学习以VGG16为例

下面是迁移代码的实现:

class VGGNet(nn.Module):
  def __init__(self, num_classes=2):  #num_classes,此处为 二分类值为2
    super(VGGNet, self).__init__()
    net = models.vgg16(pretrained=True)  #从预训练模型加载VGG16网络参数
    net.classifier = nn.Sequential() #将分类层置空,下面将改变我们的分类层
    self.features = net #保留VGG16的特征层
    self.classifier = nn.Sequential(  #定义自己的分类层
        nn.Linear(512 * 7 * 7, 512), #512 * 7 * 7不能改变 ,由VGG16网络决定的,第二个参数为神经元个数可以微调
        nn.ReLU(True),
        nn.Dropout(),
        nn.Linear(512, 128),
        nn.ReLU(True),
        nn.Dropout(),
        nn.Linear(128, num_classes),
    )

  def forward(self, x):
    x = self.features(x)
    x = x.view(x.size(0), -1)
    x = self.classifier(x)
    return x

完整代码如下

from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
import numpy as np
from torchvision import models

batch_size = 16
learning_rate = 0.0002
epoch = 10

train_transforms = transforms.Compose([
  transforms.RandomResizedCrop(224),
  transforms.RandomHorizontalFlip(),
  transforms.ToTensor(),
  transforms.Normalize((.5, .5, .5), (.5, .5, .5))
])
val_transforms = transforms.Compose([
  transforms.Resize(256),
  transforms.RandomResizedCrop(224),
  transforms.ToTensor(),
  transforms.Normalize((.5, .5, .5), (.5, .5, .5))
])

train_dir = './VGGDataSet/train'
train_datasets = datasets.ImageFolder(train_dir, transform=train_transforms)
train_dataloader = torch.utils.data.DataLoader(train_datasets, batch_size=batch_size, shuffle=True)

val_dir = './VGGDataSet/val'
val_datasets = datasets.ImageFolder(val_dir, transform=val_transforms)
val_dataloader = torch.utils.data.DataLoader(val_datasets, batch_size=batch_size, shuffle=True)

class VGGNet(nn.Module):
  def __init__(self, num_classes=3):
    super(VGGNet, self).__init__()
    net = models.vgg16(pretrained=True)
    net.classifier = nn.Sequential()
    self.features = net
    self.classifier = nn.Sequential(
        nn.Linear(512 * 7 * 7, 512),
        nn.ReLU(True),
        nn.Dropout(),
        nn.Linear(512, 128),
        nn.ReLU(True),
        nn.Dropout(),
        nn.Linear(128, num_classes),
    )

  def forward(self, x):
    x = self.features(x)
    x = x.view(x.size(0), -1)
    x = self.classifier(x)
    return x

#--------------------训练过程---------------------------------
model = VGGNet()
if torch.cuda.is_available():
  model.cuda()
params = [{'params': md.parameters()} for md in model.children()
     if md in [model.classifier]]
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
loss_func = nn.CrossEntropyLoss()

Loss_list = []
Accuracy_list = []

for epoch in range(100):
  print('epoch {}'.format(epoch + 1))
  # training-----------------------------
  train_loss = 0.
  train_acc = 0.
  for batch_x, batch_y in train_dataloader:
    batch_x, batch_y = Variable(batch_x).cuda(), Variable(batch_y).cuda()
    out = model(batch_x)
    loss = loss_func(out, batch_y)
    train_loss += loss.data[0]
    pred = torch.max(out, 1)[1]
    train_correct = (pred == batch_y).sum()
    train_acc += train_correct.data[0]
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
  print('Train Loss: {:.6f}, Acc: {:.6f}'.format(train_loss / (len(
    train_datasets)), train_acc / (len(train_datasets))))

  # evaluation--------------------------------
  model.eval()
  eval_loss = 0.
  eval_acc = 0.
  for batch_x, batch_y in val_dataloader:
    batch_x, batch_y = Variable(batch_x, volatile=True).cuda(), Variable(batch_y, volatile=True).cuda()
    out = model(batch_x)
    loss = loss_func(out, batch_y)
    eval_loss += loss.data[0]
    pred = torch.max(out, 1)[1]
    num_correct = (pred == batch_y).sum()
    eval_acc += num_correct.data[0]
  print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(
    val_datasets)), eval_acc / (len(val_datasets))))
    
	Loss_list.append(eval_loss / (len(val_datasets)))
  Accuracy_list.append(100 * eval_acc / (len(val_datasets)))

x1 = range(0, 100)
x2 = range(0, 100)
y1 = Accuracy_list
y2 = Loss_list
plt.subplot(2, 1, 1)
plt.plot(x1, y1, 'o-')
plt.title('Test accuracy vs. epoches')
plt.ylabel('Test accuracy')
plt.subplot(2, 1, 2)
plt.plot(x2, y2, '.-')
plt.xlabel('Test loss vs. epoches')
plt.ylabel('Test loss')
plt.show()
# plt.savefig("accuracy_loss.jpg")

以上这篇keras实现VGG16 CIFAR10数据集方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
python网络编程之TCP通信实例和socketserver框架使用例子
Apr 25 Python
Python实现的批量下载RFC文档
Mar 10 Python
python爬取w3shcool的JQuery课程并且保存到本地
Apr 06 Python
python读取和保存视频文件
Apr 16 Python
Python线程之定位与销毁的实现
Feb 17 Python
对python3 Serial 串口助手的接收读取数据方法详解
Jun 12 Python
Python venv虚拟环境配置过程解析
Jul 08 Python
详解python with 上下文管理器
Sep 02 Python
python如何将图片转换素描画
Sep 08 Python
python mongo 向数据中的数组类型新增数据操作
Dec 05 Python
Python实现邮件发送的详细设置方法(遇到问题)
Jan 18 Python
python manim实现排序算法动画示例
Aug 14 Python
使用darknet框架的imagenet数据分类预训练操作
Jul 07 #Python
Python调用C语言程序方法解析
Jul 07 #Python
keras实现VGG16方式(预测一张图片)
Jul 07 #Python
通过实例解析Python RPC实现原理及方法
Jul 07 #Python
Keras预训练的ImageNet模型实现分类操作
Jul 07 #Python
Scrapy模拟登录赶集网的实现代码
Jul 07 #Python
scrapy框架携带cookie访问淘宝购物车功能的实现代码
Jul 07 #Python
You might like
php 获取mysql数据库信息代码
2009/03/12 PHP
php+mysql开发中的经验与常识小结
2019/03/25 PHP
脚本吧 - 幻宇工作室用到js,超强推荐share.js
2006/12/23 Javascript
js的闭包的一个示例说明
2008/11/18 Javascript
JS验证日期的格式YYYY-mm-dd 具体实现
2013/06/29 Javascript
jquery图片轮播插件仿支付宝2013版全屏图片幻灯片
2014/04/03 Javascript
使用jquery.validate自定义方法实现"手机号码或者固话至少填写一个"的逻辑验证
2014/09/01 Javascript
C++中的string类的用法小结
2015/08/07 Javascript
jQuery插件jquery-barcode实现条码打印的方法
2015/11/25 Javascript
iOS和Android用同一个二维码实现跳转下载链接的方法
2016/09/28 Javascript
巧用Javascript的逻辑运算符
2016/12/02 Javascript
AngularJS 防止页面闪烁的方法
2017/03/09 Javascript
bootstrap Table的一些小操作
2017/11/01 Javascript
Vue入门之数据绑定(小结)
2018/01/08 Javascript
nodejs分离html文件里面的js和css的方法
2019/04/09 NodeJs
NestJs使用Mongoose对MongoDB操作的方法
2021/02/22 Javascript
Vue SPA 首屏优化方案
2021/02/26 Vue.js
[00:20]TI9不朽观赛名额抽取
2019/08/05 DOTA
python赋值操作方法分享
2013/03/23 Python
python装饰器实例大详解
2017/10/25 Python
自学python的建议和周期预算
2019/01/30 Python
python time.sleep()是睡眠线程还是进程
2019/07/09 Python
Python调用钉钉自定义机器人的实现
2020/01/03 Python
Python检测端口IP字符串是否合法
2020/06/05 Python
GUESS盖尔斯法国官网:美国时尚品牌
2016/09/23 全球购物
马来西亚和新加坡巴士票在线预订:CatchThatBus
2018/11/17 全球购物
南京某软件公司的.net面试题
2015/11/30 面试题
幼师岗位求职简历的自荐信格式
2013/09/21 职场文书
业务经理岗位职责
2013/11/11 职场文书
公司同意接收函
2014/01/13 职场文书
开业典礼主持词
2014/03/21 职场文书
2014年党支部学习材料
2014/05/19 职场文书
办公室文员岗位职责范本
2014/06/12 职场文书
个人党性锻炼总结
2015/03/05 职场文书
校运会班级霸气口号
2015/12/24 职场文书
CSS3新特性详解(五):多列columns column-count和flex布局
2021/04/30 HTML / CSS