vgg以及pytorch

vgg：

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, regularizers
import numpy as np
import os
import cv2
import matplotlib.pyplot as plt
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
resize = 224
path ="train/"

def load_data():
    imgs = os.listdir(path)
    num = len(imgs)
    train_data = np.empty((5000, resize, resize, 3), dtype="int32")
    train_label = np.empty((5000, ), dtype="int32")
    test_data = np.empty((5000, resize, resize, 3), dtype="int32")
    test_label = np.empty((5000, ), dtype="int32")
    for i in range(5000):
        if i % 2:
            train_data[i] = cv2.resize(cv2.imread(path+'/'+ 'dog.' + str(i) + '.jpg'), (resize, resize))
            train_label[i] = 1
        else:
            train_data[i] = cv2.resize(cv2.imread(path+'/' + 'cat.' + str(i) + '.jpg'), (resize, resize))
            train_label[i] = 0
    for i in range(5000, 10000):
        if i % 2:
            test_data[i-5000] = cv2.resize(cv2.imread(path+'/' + 'dog.' + str(i) + '.jpg'), (resize, resize))
            test_label[i-5000] = 1
        else:
            test_data[i-5000] = cv2.resize(cv2.imread(path+'/' + 'cat.' + str(i) + '.jpg'), (resize, resize))
            test_label[i-5000] = 0
    return train_data, train_label, test_data, test_label
def vgg16():
    weight_decay = 0.0005
    nb_epoch = 100
    batch_size = 32
    
    # layer1
    model = keras.Sequential()
    model.add(layers.Conv2D(64, (3, 3), padding='same',
                     input_shape=(224, 224, 3), kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.3))
    # layer2
    model.add(layers.Conv2D(64, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
    # layer3
    model.add(layers.Conv2D(128, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer4
    model.add(layers.Conv2D(128, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
    # layer5
    model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer6
    model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer7
    model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
    # layer8
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer9
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer10
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
    # layer11
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer12
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.Dropout(0.4))
    # layer13
    model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
    model.add(layers.Dropout(0.5))
    # layer14
    model.add(layers.Flatten())
    model.add(layers.Dense(512, kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    # layer15
    model.add(layers.Dense(512, kernel_regularizer=regularizers.l2(weight_decay)))
    model.add(layers.Activation('relu'))
    model.add(layers.BatchNormalization())
    # layer16
    model.add(layers.Dropout(0.5))
    model.add(layers.Dense(2))
    model.add(layers.Activation('softmax'))

    return model
#if __name__ == '__main__':
train_data, train_label, test_data, test_label = load_data()
train_data = train_data.astype('float32')
test_data = test_data.astype('float32')
train_label = keras.utils.to_categorical(train_label, 2)
test_label = keras.utils.to_categorical(test_label, 2)
#定义训练方法,超参数设置
model = vgg16()
sgd = tf.keras.optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) #设置优化器为SGD
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
history = model.fit(train_data, train_label,
              batch_size=20,
              epochs=10,
              validation_split=0.2,  #把训练集中的五分之一作为验证集
              shuffle=True)
scores = model.evaluate(test_data,test_label,verbose=1)
print(scores)
model.save('model/vgg16dogcat.h5')
acc = history.history['accuracy']  # 获取训练集准确性数据
val_acc = history.history['val_accuracy']  # 获取验证集准确性数据
loss = history.history['loss']  # 获取训练集错误值数据
val_loss = history.history['val_loss']  # 获取验证集错误值数据
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Trainning acc')  # 以epochs为横坐标，以训练集准确性为纵坐标
plt.plot(epochs, val_acc, 'b', label='Vaildation acc')  # 以epochs为横坐标，以验证集准确性为纵坐标
plt.legend()  # 绘制图例，即标明图中的线段代表何种含义
 
plt.show()

 

 

 

 

pytorch：

import torch
import torchvision
import torchvision.transforms as transforms
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
import matplotlib.pyplot as plt
import numpy as np

# functions to show an image


def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()
import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

outputs = net(images)
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Assume that we are on a CUDA machine, then this should print a CUDA device:

print(device)
net.to(device)
inputs, labels = inputs.to(device), labels.to(device)