keras实现VGG16 CIFAR10数据集方式

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)

#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)

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

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")