keras实现用vgg非预训练模型对四种天气分类，能够自己定义归一化方法，并绘制图像

好的，下面是代码实现：

首先，我们需要导入相关的库和数据集。

import os
import numpy as np
import matplotlib.pyplot as plt

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import Adam

train_dir = 'weather/train'
validation_dir = 'weather/validation'
test_dir = 'weather/test'

train_datagen = ImageDataGenerator(rescale=1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_dir,
        target_size=(224, 224),
        batch_size=32,
        class_mode='categorical')

validation_generator = validation_datagen.flow_from_directory(
        validation_dir,
        target_size=(224, 224),
        batch_size=32,
        class_mode='categorical')

test_generator = test_datagen.flow_from_directory(
        test_dir,
        target_size=(224, 224),
        batch_size=32,
        class_mode='categorical')

接下来，我们定义一个 VGG 非预训练模型。

model = Sequential()

# Block 1
model.add(Conv2D(64, (3, 3), padding='same', input_shape=(224, 224, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# Block 2
model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# Block 3
model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(256, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# Block 4
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

# Block 5
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(Conv2D(512, (3, 3), padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())

# Fully connected layer
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4, activation='softmax'))

model.summary()

接下来，我们定义模型的优化器和损失函数。

adam = Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])

然后，我们开始训练模型。

history = model.fit_generator(
        train_generator,
        steps_per_epoch=100,
        epochs=10,
        validation_data=validation_generator,
        validation_steps=50)

最后，我们可以绘制损失函数和准确率随着训练迭代次数的变化图像。

# 绘制训练集和验证集的损失函数和准确率
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()

plt.show()