博客

下面是详细讲解“keras模型保存为tensorflow的二进制模型方式”的完整攻略。

1. 模型训练

首先，我们需要使用Keras框架进行模型的训练。这里我们以一个简单的手写体数字识别模型为例：

from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)

model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=tf.keras.losses.categorical_crossentropy,
              optimizer=tf.keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))

这里我们使用了两层卷积神经网络，Dropout和全连接层。我们训练好了模型后，需要将其保存为 TensorFlow 的二进制模型。

2. 保存模型

TensorFlow提供了两个API来保存模型：SavedModel和tf.train.Checkpoint。这里我们主要介绍SavedModel。

SavedModel是序列化模型的格式，可以将模型的结构、权重和训练配置保存为文件夹。使用SavedModel格式保存模型有以下几个步骤：

2.1 路径设置

创建一个用于保存模型的文件夹路径：

import os

# 创建文件夹
export_path = './saved_model'
if os.path.isdir(export_path):
    print('已经存在')
else:
    os.mkdir(export_path)  # 如果文件夹不存在，则创建

2.2 保存模型

使用 tf.keras.models.save_model() 函数将模型保存到文件夹路径中，并设置 save_format='tf' 参数。

tf.keras.models.save_model(
    model,
    export_path,
    save_format='tf'
)

这会将模型及其所有权重和配置保存到文件夹路径中。

2.3 恢复模型

要使用保存的模型，可以使用 tf.keras.models.load_model() 函数，其参数是保存的文件夹路径：

loaded_model = tf.keras.models.load_model(export_path)

这将返回一个与保存模型相同的模型对象。可以使用该模型对象完成推断或微调等后续操作。

3. 示例说明

下面给出两个示例说明：

3.1 保存和恢复MNIST模型

import tensorflow as tf

from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import backend as K
import os

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)

model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=tf.keras.losses.categorical_crossentropy,
              optimizer=tf.keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))

# 保存模型
export_path = './saved_model/mnist'
if not os.path.exists(export_path):
    os.makedirs(export_path)
tf.keras.models.save_model(model, export_path, save_format='tf')

# 加载模型
loaded_model = tf.keras.models.load_model(export_path)

# 用测试数据进行推断
score = loaded_model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

3.2 保存和恢复CIFAR10模型

import tensorflow as tf

from tensorflow.keras.datasets import cifar10
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Conv2D, Dense, Flatten, MaxPooling2D
from tensorflow.keras.models import Sequential
import os

# 加载 CIFAR-10 数据集
(x_train, y_train), (x_test, y_test) = cifar10.load_data()

# 数据预处理，将像素值缩放到 [0, 1] 区间
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255

# 将类别标签转换为 one-hot 向量
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# 构建模型
model = Sequential([
    Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
    Conv2D(32, (3, 3), activation='relu'),
    MaxPooling2D(pool_size=(2, 2)),
    Dropout(0.25),

    Conv2D(64, (3, 3), activation='relu'),
    Conv2D(64, (3, 3), activation='relu'),
    MaxPooling2D(pool_size=(2, 2)),
    Dropout(0.25),

    Flatten(),
    Dense(512, activation='relu'),
    Dropout(0.5),
    Dense(10, activation='softmax'),
])

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

model.fit(x_train, y_train,
          batch_size=64,
          epochs=10,
          validation_data=(x_test, y_test))

# 保存模型
export_path = './saved_model/cifar10'
if not os.path.exists(export_path):
    os.makedirs(export_path)
tf.keras.models.save_model(model, export_path, save_format='tf')

# 加载模型
loaded_model = tf.keras.models.load_model(export_path)

# 用测试数据进行推断
score = loaded_model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

以上两个示例代码中，我们都先用Keras训练了一个模型，然后将模型保存为 TensorFlow 的二进制模型格式。再用 tf.keras.models.load_model() 加载保存的模型，并用测试数据进行推断。这里的方法可以适用于大多数Keras模型。