Sequential 模型

作者: fchollet

在 TensorFlow.org 上檢視 在 Google Colab 中執行 在 GitHub 上檢視原始碼 在 keras.io 上檢視

設定

import tensorflow as tf
import keras
from keras import layers

何時使用 Sequential 模型

Sequential 模型適用於純粹的層堆疊,其中每一層都只有一個輸入張量和一個輸出張量

以下 Sequential 模型示意圖

# Define Sequential model with 3 layers
model = keras.Sequential(
    [
        layers.Dense(2, activation="relu", name="layer1"),
        layers.Dense(3, activation="relu", name="layer2"),
        layers.Dense(4, name="layer3"),
    ]
)
# Call model on a test input
x = tf.ones((3, 3))
y = model(x)

相當於這個函式

# Create 3 layers
layer1 = layers.Dense(2, activation="relu", name="layer1")
layer2 = layers.Dense(3, activation="relu", name="layer2")
layer3 = layers.Dense(4, name="layer3")

# Call layers on a test input
x = tf.ones((3, 3))
y = layer3(layer2(layer1(x)))

在下列情況下,Sequential 模型不適用

  • 您的模型有多個輸入或多個輸出
  • 您的任何層有多個輸入或多個輸出
  • 您需要進行層共用
  • 您想要非線性拓撲 (例如殘差連線、多分支模型)

建立 Sequential 模型

您可以將層清單傳遞至 Sequential 建構函式來建立 Sequential 模型

model = keras.Sequential(
    [
        layers.Dense(2, activation="relu"),
        layers.Dense(3, activation="relu"),
        layers.Dense(4),
    ]
)

其層可透過 layers 屬性存取

model.layers
[<keras.src.layers.core.dense.Dense at 0x7fa3c8de0100>,
 <keras.src.layers.core.dense.Dense at 0x7fa3c8de09a0>,
 <keras.src.layers.core.dense.Dense at 0x7fa5181b5c10>]

您也可以透過 add() 方法以累加方式建立 Sequential 模型

model = keras.Sequential()
model.add(layers.Dense(2, activation="relu"))
model.add(layers.Dense(3, activation="relu"))
model.add(layers.Dense(4))

請注意,還有對應的 pop() 方法可移除層:Sequential 模型非常像層清單。

model.pop()
print(len(model.layers))  # 2
2

另請注意,Sequential 建構函式接受 name 引數,就像 Keras 中的任何層或模型一樣。這對於使用語意上有意義的名稱註解 TensorBoard 圖表非常有用。

model = keras.Sequential(name="my_sequential")
model.add(layers.Dense(2, activation="relu", name="layer1"))
model.add(layers.Dense(3, activation="relu", name="layer2"))
model.add(layers.Dense(4, name="layer3"))

預先指定輸入形狀

一般來說,Keras 中的所有層都需要知道其輸入的形狀,才能建立其權重。因此,當您像這樣建立層時,一開始它沒有權重

layer = layers.Dense(3)
layer.weights  # Empty
[]

它會在第一次對輸入呼叫時建立其權重,因為權重的形狀取決於輸入的形狀

# Call layer on a test input
x = tf.ones((1, 4))
y = layer(x)
layer.weights  # Now it has weights, of shape (4, 3) and (3,)
[<tf.Variable 'dense_6/kernel:0' shape=(4, 3) dtype=float32, numpy=
 array([[ 0.1752373 ,  0.47623062,  0.24374962],
        [-0.0298934 ,  0.50255656,  0.78478384],
        [-0.58323103, -0.56861055, -0.7190975 ],
        [-0.3191281 , -0.23635858, -0.8841506 ]], dtype=float32)>,
 <tf.Variable 'dense_6/bias:0' shape=(3,) dtype=float32, numpy=array([0., 0., 0.], dtype=float32)>]

當然,這也適用於 Sequential 模型。當您在沒有輸入形狀的情況下具現化 Sequential 模型時,它不會「建構」:它沒有權重 (且呼叫 model.weights 會導致錯誤,說明了這一點)。權重會在模型第一次看到一些輸入資料時建立

model = keras.Sequential(
    [
        layers.Dense(2, activation="relu"),
        layers.Dense(3, activation="relu"),
        layers.Dense(4),
    ]
)  # No weights at this stage!

# At this point, you can't do this:
# model.weights

# You also can't do this:
# model.summary()

# Call the model on a test input
x = tf.ones((1, 4))
y = model(x)
print("Number of weights after calling the model:", len(model.weights))  # 6
Number of weights after calling the model: 6

模型「建構」完成後,您可以呼叫其 summary() 方法來顯示其內容

model.summary()
Model: "sequential_3"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense_7 (Dense)             (1, 2)                    10        
                                                                 
 dense_8 (Dense)             (1, 3)                    9         
                                                                 
 dense_9 (Dense)             (1, 4)                    16        
                                                                 
=================================================================
Total params: 35 (140.00 Byte)
Trainable params: 35 (140.00 Byte)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

但是,以累加方式建構 Sequential 模型時,能夠顯示模型的摘要 (包括目前的輸出形狀) 會非常有用。在這種情況下,您應該從將 Input 物件傳遞至模型開始,以便模型從一開始就知道其輸入形狀

model = keras.Sequential()
model.add(keras.Input(shape=(4,)))
model.add(layers.Dense(2, activation="relu"))

model.summary()
Model: "sequential_4"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense_10 (Dense)            (None, 2)                 10        
                                                                 
=================================================================
Total params: 10 (40.00 Byte)
Trainable params: 10 (40.00 Byte)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

請注意,Input 物件不會顯示為 model.layers 的一部分,因為它不是層

model.layers
[<keras.src.layers.core.dense.Dense at 0x7fa3bc0ba820>]

一個簡單的替代方法是將 input_shape 引數傳遞至您的第一層

model = keras.Sequential()
model.add(layers.Dense(2, activation="relu", input_shape=(4,)))

model.summary()
Model: "sequential_5"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense_11 (Dense)            (None, 2)                 10        
                                                                 
=================================================================
Total params: 10 (40.00 Byte)
Trainable params: 10 (40.00 Byte)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

以此類預先定義的輸入形狀建構的模型,始終具有權重 (即使在看到任何資料之前),並且始終具有已定義的輸出形狀。

一般來說,如果您知道 Sequential 模型的輸入形狀,建議的最佳做法是始終預先指定輸入形狀。

常見的偵錯工作流程:add() + summary()

在建構新的 Sequential 架構時,以累加方式透過 add() 堆疊層並經常列印模型摘要非常有用。例如,這可讓您監控 Conv2DMaxPooling2D 層堆疊如何對影像特徵圖進行降採樣

model = keras.Sequential()
model.add(keras.Input(shape=(250, 250, 3)))  # 250x250 RGB images
model.add(layers.Conv2D(32, 5, strides=2, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(3))

# Can you guess what the current output shape is at this point? Probably not.
# Let's just print it:
model.summary()

# The answer was: (40, 40, 32), so we can keep downsampling...

model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(3))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(2))

# And now?
model.summary()

# Now that we have 4x4 feature maps, time to apply global max pooling.
model.add(layers.GlobalMaxPooling2D())

# Finally, we add a classification layer.
model.add(layers.Dense(10))
Model: "sequential_6"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv2d (Conv2D)             (None, 123, 123, 32)      2432      
                                                                 
 conv2d_1 (Conv2D)           (None, 121, 121, 32)      9248      
                                                                 
 max_pooling2d (MaxPooling2  (None, 40, 40, 32)        0         
 D)                                                              
                                                                 
=================================================================
Total params: 11680 (45.62 KB)
Trainable params: 11680 (45.62 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________
Model: "sequential_6"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv2d (Conv2D)             (None, 123, 123, 32)      2432      
                                                                 
 conv2d_1 (Conv2D)           (None, 121, 121, 32)      9248      
                                                                 
 max_pooling2d (MaxPooling2  (None, 40, 40, 32)        0         
 D)                                                              
                                                                 
 conv2d_2 (Conv2D)           (None, 38, 38, 32)        9248      
                                                                 
 conv2d_3 (Conv2D)           (None, 36, 36, 32)        9248      
                                                                 
 max_pooling2d_1 (MaxPoolin  (None, 12, 12, 32)        0         
 g2D)                                                            
                                                                 
 conv2d_4 (Conv2D)           (None, 10, 10, 32)        9248      
                                                                 
 conv2d_5 (Conv2D)           (None, 8, 8, 32)          9248      
                                                                 
 max_pooling2d_2 (MaxPoolin  (None, 4, 4, 32)          0         
 g2D)                                                            
                                                                 
=================================================================
Total params: 48672 (190.12 KB)
Trainable params: 48672 (190.12 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

非常實用,對吧?

擁有模型後該怎麼做

模型架構準備就緒後,您會想要

使用 Sequential 模型進行特徵擷取

建構 Sequential 模型後,它的行為就像 Functional API 模型。這表示每一層都有 inputoutput 屬性。這些屬性可用於執行巧妙的操作,例如快速建立一個模型,擷取 Sequential 模型中所有中繼層的輸出

initial_model = keras.Sequential(
    [
        keras.Input(shape=(250, 250, 3)),
        layers.Conv2D(32, 5, strides=2, activation="relu"),
        layers.Conv2D(32, 3, activation="relu"),
        layers.Conv2D(32, 3, activation="relu"),
    ]
)
feature_extractor = keras.Model(
    inputs=initial_model.inputs,
    outputs=[layer.output for layer in initial_model.layers],
)

# Call feature extractor on test input.
x = tf.ones((1, 250, 250, 3))
features = feature_extractor(x)

以下是一個類似範例,僅從一層擷取特徵

initial_model = keras.Sequential(
    [
        keras.Input(shape=(250, 250, 3)),
        layers.Conv2D(32, 5, strides=2, activation="relu"),
        layers.Conv2D(32, 3, activation="relu", name="my_intermediate_layer"),
        layers.Conv2D(32, 3, activation="relu"),
    ]
)
feature_extractor = keras.Model(
    inputs=initial_model.inputs,
    outputs=initial_model.get_layer(name="my_intermediate_layer").output,
)
# Call feature extractor on test input.
x = tf.ones((1, 250, 250, 3))
features = feature_extractor(x)

使用 Sequential 模型進行遷移學習

遷移學習包括凍結模型中的底層,僅訓練頂層。如果您不熟悉遷移學習,請務必閱讀我們的遷移學習指南

以下是兩個常見的遷移學習藍圖,涉及 Sequential 模型。

首先,假設您有一個 Sequential 模型,並且想要凍結除最後一層以外的所有層。在這種情況下,您只需疊代 model.layers 並在每一層上設定 layer.trainable = False,除了最後一層。像這樣

model = keras.Sequential([
    keras.Input(shape=(784)),
    layers.Dense(32, activation='relu'),
    layers.Dense(32, activation='relu'),
    layers.Dense(32, activation='relu'),
    layers.Dense(10),
])

# Presumably you would want to first load pre-trained weights.
model.load_weights(...)

# Freeze all layers except the last one.
for layer in model.layers[:-1]:
  layer.trainable = False

# Recompile and train (this will only update the weights of the last layer).
model.compile(...)
model.fit(...)

另一個常見的藍圖是使用 Sequential 模型來堆疊預先訓練的模型和一些新初始化的分類層。像這樣

# Load a convolutional base with pre-trained weights
base_model = keras.applications.Xception(
    weights='imagenet',
    include_top=False,
    pooling='avg')

# Freeze the base model
base_model.trainable = False

# Use a Sequential model to add a trainable classifier on top
model = keras.Sequential([
    base_model,
    layers.Dense(1000),
])

# Compile & train
model.compile(...)
model.fit(...)

如果您進行遷移學習,您可能會發現自己經常使用這兩種模式。

這就是您需要了解的關於 Sequential 模型的所有資訊!

若要深入瞭解如何在 Keras 中建構模型,請參閱