keras 创建模型的三种方法

在TensorFlow的官方网站中给出了三种创建网络模型的方法，汇总记录如下。

第一种 . 直接创建法

# 创建模型
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10)
])

# 编译模型
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 训练模型
model.fit(train_images, train_labels, epochs=10)

# 评估模型
test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)

# 使用模型进行预测
probability_model = tf.keras.Sequential([model, 
                                         tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)

第二种. 添加网络法

# 创建网络模型
vocab_size = 10000

model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation='relu'))
model.add(keras.layers.Dense(1, activation='sigmoid'))

model.summary()


# 编译网络模型
model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])


# 训练网络模型
history = model.fit(partial_x_train,
                    partial_y_train,
                    epochs=40,
                    batch_size=512,
                    validation_data=(x_val, y_val),
                    verbose=1)

# 评估网络模型
results = model.evaluate(test_data,  test_labels, verbose=2)

第三种 . 使用 keras.Model函数创建

定义模型

OUTPUT_CHANNELS = 3

base_model = tf.keras.applications.MobileNetV2(input_shape=[128, 128, 3], include_top=False)

# 使用这些层的激活设置
layer_names = [
    'block_1_expand_relu',   # 64x64
    'block_3_expand_relu',   # 32x32
    'block_6_expand_relu',   # 16x16
    'block_13_expand_relu',  # 8x8
    'block_16_project',      # 4x4
]
layers = [base_model.get_layer(name).output for name in layer_names]

# 创建特征提取模型
down_stack = tf.keras.Model(inputs=base_model.input, outputs=layers)

down_stack.trainable = False

up_stack = [
    pix2pix.upsample(512, 3),  # 4x4 -> 8x8
    pix2pix.upsample(256, 3),  # 8x8 -> 16x16
    pix2pix.upsample(128, 3),  # 16x16 -> 32x32
    pix2pix.upsample(64, 3),   # 32x32 -> 64x64
]

def unet_model(output_channels):
  inputs = tf.keras.layers.Input(shape=[128, 128, 3])
  x = inputs

  # 在模型中降频取样
  skips = down_stack(x)
  x = skips[-1]
  skips = reversed(skips[:-1])

  # 升频取样然后建立跳跃连接
  for up, skip in zip(up_stack, skips):
    x = up(x)
    concat = tf.keras.layers.Concatenate()
    x = concat([x, skip])

  # 这是模型的最后一层
  last = tf.keras.layers.Conv2DTranspose(
      output_channels, 3, strides=2,
      padding='same')  #64x64 -> 128x128

  x = last(x)

  return tf.keras.Model(inputs=inputs, outputs=x)

创建并编译模型

model = unet_model(OUTPUT_CHANNELS)
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

 

第四种. 自定义图层方法

# 创建一个网络层的类
class MyDenseLayer(tf.keras.layers.Layer):
  def __init__(self, num_outputs):
    super(MyDenseLayer, self).__init__()
    self.num_outputs = num_outputs

  def build(self, input_shape):
    self.kernel = self.add_weight("kernel",
                                  shape=[int(input_shape[-1]),
                                         self.num_outputs])

  def call(self, inputs):
    return tf.matmul(inputs, self.kernel)

# 
layer = MyDenseLayer(10)