Python 在Keras中保存模型的正确方法

我一直试图在研究中实施迁移学习。我决定使用

keras.applications

中提供的VGG16

我加载模型并冻结其权重，如下所示：

vgg16=vgg16（weights='imagenet'，include_top=False，input_shape=（img_行，img_列，3），pooling=None）
对于vgg16.layers中的层：
layer.trainable=错误

然后添加顶层进行分类：

model = Sequential()
model.add(vgg16)
model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

我根据我的数据编译并训练模型，以便首先预热顶层：

EPOCHS = 4000

history = model.fit_generator(datagen_train.flow(X_train, y_train, batch_size=100),
                        validation_data = datagen_val.flow(X_val, y_val, batch_size=100),
                        epochs = EPOCHS,
                        steps_per_epoch = np.ceil(len(X_train) / 100),
                        validation_steps = np.ceil(len(X_val) / 100),
                        callbacks=[es, mc]
                       )

我使用常用的Keras命令保存模型：

save\u model

我的下一个目标是解冻VGG16的一些顶层，并再次训练模型（也称为微调）。但是，在使用

load\u model

加载模型时，我发现该模型看起来像未经培训的。我在保存测试数据集之前对其进行了测试，性能在70%范围内很高。加载相同的模型后，我发现测试数据集的性能大约为20%，这几乎低于概率，因为我有五个类标签

---

在我的

save\u model

和

load\u model

命令之间发生了什么

Keras支持一个更简单的界面，将模型权重和模型架构一起保存到单个H5文件中

使用save.model方式保存模型包括我们需要了解的关于模型的所有信息，包括：

模型权重

模型架构

模型编译详细信息（损失和指标）

模型优化器状态

然后可以通过调用load_model（）函数并传递文件名来加载保存的模型。该函数返回具有相同体系结构和权重的模型

示例：我运行了一个简单的模型，并使用model.save保存，使用keras的load_模型加载。您可以从下载数据集

构建并保存模型：

# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
model.summary()

# Fit the model
model.fit(X, Y, epochs=150, batch_size=10, verbose=0)

# evaluate the model
scores = model.evaluate(X, Y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

# save model and architecture to single file
model.save("model.h5")
print("Saved model to disk")

# load and evaluate a saved model
from numpy import loadtxt
from keras.models import load_model

# load model
model = load_model('model.h5')

# summarize model.
model.summary()

# load dataset
dataset = loadtxt("pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# evaluate the model
score = model.evaluate(X, Y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], score[1]*100))

输出-

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_7 (Dense)              (None, 12)                108       
_________________________________________________________________
dense_8 (Dense)              (None, 8)                 104       
_________________________________________________________________
dense_9 (Dense)              (None, 1)                 9         
=================================================================
Total params: 221
Trainable params: 221
Non-trainable params: 0
_________________________________________________________________
acc: 77.08%
Saved model to disk

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_7 (Dense)              (None, 12)                108       
_________________________________________________________________
dense_8 (Dense)              (None, 8)                 104       
_________________________________________________________________
dense_9 (Dense)              (None, 1)                 9         
=================================================================
Total params: 221
Trainable params: 221
Non-trainable params: 0
_________________________________________________________________
acc: 77.08%

加载模型并评估以验证：

# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
model.summary()

# Fit the model
model.fit(X, Y, epochs=150, batch_size=10, verbose=0)

# evaluate the model
scores = model.evaluate(X, Y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

# save model and architecture to single file
model.save("model.h5")
print("Saved model to disk")

# load and evaluate a saved model
from numpy import loadtxt
from keras.models import load_model

# load model
model = load_model('model.h5')

# summarize model.
model.summary()

# load dataset
dataset = loadtxt("pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# evaluate the model
score = model.evaluate(X, Y, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], score[1]*100))

输出-

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_7 (Dense)              (None, 12)                108       
_________________________________________________________________
dense_8 (Dense)              (None, 8)                 104       
_________________________________________________________________
dense_9 (Dense)              (None, 1)                 9         
=================================================================
Total params: 221
Trainable params: 221
Non-trainable params: 0
_________________________________________________________________
acc: 77.08%
Saved model to disk

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_7 (Dense)              (None, 12)                108       
_________________________________________________________________
dense_8 (Dense)              (None, 8)                 104       
_________________________________________________________________
dense_9 (Dense)              (None, 1)                 9         
=================================================================
Total params: 221
Trainable params: 221
Non-trainable params: 0
_________________________________________________________________
acc: 77.08%

---

试试

model.save（）

和

load\u model（）

。这正是我使用的。我已经找到了问题的原因。保存模型并将其加载回进行微调后，我使用fit方法开始对其进行训练。结果证明，优化算法很快就把它带向了错误的方向，尽管我已经将相对较低的学习率设置为0.0001。我通过进一步降低学习速度来修复它。加载后不需要编译。它将使用正确的优化器状态自动编译。