keras實現(xiàn)VGG16 CIFAR10數(shù)據(jù)集方式

更新時間：2020年07月07日 10:50:22 作者：「已注銷」

這篇文章主要介紹了keras實現(xiàn)VGG16 CIFAR10數(shù)據(jù)集方式，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

我就廢話不多說了，大家還是直接看代碼吧！

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)

補充知識：pytorch一步一步在VGG16上訓練自己的數(shù)據(jù)集

準備數(shù)據(jù)集及加載，ImageFolder

在很多機器學習或者深度學習的任務中，往往我們要提供自己的圖片。也就是說我們的數(shù)據(jù)集不是預先處理好的，像mnist，cifar10等它已經(jīng)給你處理好了，更多的是原始的圖片。比如我們以貓狗分類為例。在data文件下，有兩個分別為train和val的文件夾。然后train下是cat和dog兩個文件夾，里面存的是自己的圖片數(shù)據(jù)，val文件夾同train。這樣我們的數(shù)據(jù)集就準備好了。

ImageFolder能夠以目錄名作為標簽來對數(shù)據(jù)集做劃分，下面是pytorch中文文檔中關于ImageFolder的介紹：

#對訓練集做一個變換
train_transforms = transforms.Compose([
  transforms.RandomResizedCrop(224), #對圖片尺寸做一個縮放切割
  transforms.RandomHorizontalFlip(), #水平翻轉
  transforms.ToTensor(),   #轉化為張量
  transforms.Normalize((.5, .5, .5), (.5, .5, .5)) #進行歸一化
])
#對測試集做變換
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"      #訓練集路徑
#定義數(shù)據(jù)集
train_datasets = datasets.ImageFolder(train_dir, transform=train_transforms)
#加載數(shù)據(jù)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)

遷移學習以VGG16為例

下面是遷移代碼的實現(xiàn)：

class VGGNet(nn.Module):
  def __init__(self, num_classes=2):  #num_classes，此處為 二分類值為2
    super(VGGNet, self).__init__()
    net = models.vgg16(pretrained=True)  #從預訓練模型加載VGG16網(wǎng)絡參數(shù)
    net.classifier = nn.Sequential() #將分類層置空，下面將改變我們的分類層
    self.features = net #保留VGG16的特征層
    self.classifier = nn.Sequential(  #定義自己的分類層
        nn.Linear(512 * 7 * 7, 512), #512 * 7 * 7不能改變 ，由VGG16網(wǎng)絡決定的，第二個參數(shù)為神經(jīng)元個數(shù)可以微調
        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

完整代碼如下

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

#--------------------訓練過程---------------------------------
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")

以上這篇keras實現(xiàn)VGG16 CIFAR10數(shù)據(jù)集方式就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: