VGG、PyTorch神经网络以及图像分类器

• VGG

#从keras.model中导入model模块，为函数api搭建网络做准备
from tensorflow.keras import Model
from tensorflow.keras.layers import Flatten,Dense,Dropout,MaxPooling2D,Conv2D,BatchNormalization,Input,ZeroPadding2D,Concatenate
from tensorflow.keras import *
from tensorflow.keras import regularizers  #正则化
from tensorflow.keras.optimizers import RMSprop  #优化选择器
from tensorflow.keras.layers import AveragePooling2D
from tensorflow.keras.datasets import mnist
import matplotlib.pyplot as plt
import numpy as np
from tensorflow.python.keras.utils import np_utils

#数据处理
(X_train,Y_train),(X_test,Y_test)=mnist.load_data()
X_test1=X_test
Y_test1=Y_test
X_train=X_train.reshape(-1,28,28,1).astype("float32")/255.0
X_test=X_test.reshape(-1,28,28,1).astype("float32")/255.0
Y_train=np_utils.to_categorical(Y_train,10)
Y_test=np_utils.to_categorical(Y_test,10)
print(X_train.shape)
print(Y_train.shape)
print(X_train.shape)

 

 

def vgg16():
    x_input = Input((28, 28, 1))  # 输入数据形状28*28*1
    # Block 1
    x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(x_input)
    x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)

    # Block 2
    x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
    x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)

    # Block 3
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
    x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)

    # Block 4
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
    x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)

    # Block 5
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
    x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)

    #BLOCK 6
    x=Flatten()(x)
    x=Dense(256,activation="relu")(x)
    x=Dropout(0.5)(x)
    x = Dense(256, activation="relu")(x)
    x = Dropout(0.5)(x)
    #搭建最后一层，即输出层
    x = Dense(10, activation="softmax")(x)
    # 调用MDOEL函数，定义该网络模型的输入层为X_input,输出层为x.即全连接层
    model = Model(inputs=x_input, outputs=x)
    # 查看网络模型的摘要
    model.summary()
    return model

model=vgg16()
optimizer=RMSprop(lr=1e-4)
model.compile(loss="binary_crossentropy",optimizer=optimizer,metrics=["accuracy"])
#训练加评估模型
n_epoch=4
batch_size=128
def run_model(): #训练模型
    training=model.fit(
    X_train,
    Y_train,
    batch_size=batch_size,
    epochs=n_epoch,
    validation_split=0.25,
    verbose=1
    )
    test=model.evaluate(X_train,Y_train,verbose=1)
    return training,test
training,test=run_model()
print("误差：",test[0])
print("准确率：",test[1])

 

 

def show_train(training_history,train, validation):
    plt.plot(training.history[train],linestyle="-",color="b")
    plt.plot(training.history[validation] ,linestyle="--",color="r")
    plt.title("training history")
    plt.xlabel("epoch")
    plt.ylabel("accuracy")
    plt.legend(["training","validation"],loc="lower right")
    plt.show()
show_train(training,"accuracy","val_accuracy")

 

 

def show_train1(training_history,train, validation):
    plt.plot(training.history[train],linestyle="-",color="b")
    plt.plot(training.history[validation] ,linestyle="--",color="r")
    plt.title("training history")
    plt.xlabel("epoch")
    plt.ylabel("loss")
    plt.legend(["training","validation"],loc="upper right")
    plt.show()
show_train1(training,"loss","val_loss")

 

 

prediction=model.predict(X_test)
def image_show(image):
    fig=plt.gcf()  #获取当前图像
    fig.set_size_inches(2,2)  #改变图像大小
    plt.imshow(image,cmap="binary")  #显示图像
    plt.show()
def result(i):
    image_show(X_test1[i])
    print("真实值：",Y_test1[i])
    print("预测值：",np.argmax(prediction[i]))
result(0)
result(1)

 

• PyTorch神经网络以及图像分类器

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


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)

 

 

params = list(net.parameters())
print(len(params))
print(params[0].size())  # conv1's .weight

 

 

input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)

 

 

net.zero_grad()
out.backward(torch.randn(1, 10))

output = net(input)
target = torch.randn(10)  # a dummy target, for example
target = target.view(1, -1)  # make it the same shape as output
criterion = nn.MSELoss()

loss = criterion(output, target)
print(loss)

 

 

print(loss.grad_fn)  # MSELoss
print(loss.grad_fn.next_functions[0][0])  # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])  # ReLU

 

 

net.zero_grad()     # zeroes the gradient buffers of all parameters

print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)

loss.backward()

print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)

 

 

learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data * learning_rate)


import torch.optim as optim

# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()   # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()    # Does the update    

• PyTorch图像分类器

import torch
import torchvision
import torchvision.transforms as transforms


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]))