keras实现用resnet18非预训练模型对四种天气分类cpu版本，并绘制图像

首先需要导入相关的库：

import tensorflow as tf
from tensorflow.keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
from tensorflow.keras.models import Sequential
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam

然后创建一个模型：

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

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

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

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

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

    # Flatten
    model.add(Flatten())
    model.add(Dense(4096, activation='relu'))
    model.add(Dense(4096, activation='relu'))
    model.add(Dense(4, activation='softmax'))

    return model

接着使用ImageDataGenerator来加载数据：

train_data_generator = ImageDataGenerator(
    rescale=1./255, 
    shear_range=0.2, 
    zoom_range=0.2, 
    horizontal_flip=True
)

test_data_generator = ImageDataGenerator(rescale=1./255)

train_data = train_data_generator.flow_from_directory(
    'train',
    target_size=(224, 224),
    batch_size=32,
    class_mode='categorical'
)

test_data = test_data_generator.flow_from_directory(
    'test',
    target_size=(224, 224),
    batch_size=32,
    class_mode='categorical'
)

然后创建模型并编译：

model = create_model()
model.compile(optimizer=Adam(learning_rate=0.001), loss='categorical_crossentropy', metrics=['accuracy'])

最后训练模型并绘制图像：

history = model.fit(
    train_data,
    epochs=10,
    validation_data=test_data
)

# 绘制训练集和验证集的准确率和损失值曲线
import matplotlib.pyplot as plt

plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('Model Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend(['Train', 'Val'], loc='upper left')
plt.show()

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend(['Train', 'Val'], loc='upper left')
plt.show()

这样就完成了用resnet18非预训练模型对四种天气分类的任务，并绘制了相应的图像。