主流迁移学习模型微调优化的解决方案_迁移学习都有哪些模型

# 导入所需的库

import tensorflow as tf

from tensorflow.keras.applications import VGG16

from tensorflow.keras.models import Model

from tensorflow.keras.layers import Dense, Dropout, Flatten

from tensorflow.keras.optimizers import SGD

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# 加载预训练模型

base_model = VGG16(weights='imagenet', include_top=False, input_shape=(224, 224, 3))

# 冻结预训练模型的参数

for layer in base_model.layers:

layer.trainable = False

# 添加新的全连接层

x = base_model.output

x = Flatten()(x)

x = Dense(256, activation='relu')(x)

x = Dropout(0.5)(x)

predictions = Dense(10, activation='softmax')(x)

# 构建新的模型

model = Model(inputs=base_model.input, outputs=predictions)

# 编译模型

model.compile(optimizer=SGD(lr=0.001, momentum=0.9), loss='categorical_crossentropy', metrics=['accuracy'])

# 数据增强

train_datagen = ImageDataGenerator(

rescale=1./255,

shear_range=0.2,

zoom_range=0.2,

horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(

'data/train',

target_size=(224, 224),

batch_size=32,

class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(

'data/validation',

target_size=(224, 224),

batch_size=32,

class_mode='categorical')

# 模型训练

model.fit(

train_generator,

steps_per_epoch=2000,

epochs=50,

validation_data=validation_generator,

validation_steps=800)

# 保存模型

model.save('fine_tuned_model.h5')