How can I use tf.keras.Model.summary to see the layers of a child model which in a father model?

Question

我有一個 tf.keras.Model 的子類 Model，代碼如下

import tensorflow as tf


class Mymodel(tf.keras.Model):

    def __init__(self, classes, backbone_model, *args, **kwargs):
        super(Mymodel, self).__init__(self, args, kwargs)
        self.backbone = backbone_model
        self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')

    def call(self, inputs):
        x = self.backbone(inputs)
        x = self.classify_layer(x)
        return x

inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61, 
                backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()

結果是：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
mobilenet_1.00_224 (Model)   (None, 1000)              4253864   
_________________________________________________________________
dense (Dense)                multiple                  61061     
=================================================================
Total params: 4,314,925
Trainable params: 4,293,037
Non-trainable params: 21,888
_________________________________________________________________

但我想查看mobilenet的所有層，然后我嘗試提取mobilenet的所有層並放入model：

import tensorflow as tf


class Mymodel(tf.keras.Model):

    def __init__(self, classes, backbone_model, *args, **kwargs):
        super(Mymodel, self).__init__(self, args, kwargs)
        self.backbone = backbone_model
        self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')

    def my_process_layers(self,inputs):
        layers = self.backbone.layers
        tmp_x = inputs
        for i in range(1,len(layers)):
            tmp_x = layers[i](tmp_x)
        return tmp_x

    def call(self, inputs):
        x = self.my_process_layers(inputs)
        x = self.classify_layer(x)
        return x

inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61, 
                backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()

然后結果沒有改變。

    _________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
mobilenet_1.00_224 (Model)   (None, 1000)              4253864   
_________________________________________________________________
dense (Dense)                multiple                  61061     
=================================================================
Total params: 4,314,925
Trainable params: 4,293,037
Non-trainable params: 21,888
_________________________________________________________________

然后我嘗試將一層插入提取到 model：

import tensorflow as tf


class Mymodel(tf.keras.Model):

    def __init__(self, classes, backbone_model, *args, **kwargs):
        super(Mymodel, self).__init__(self, args, kwargs)
        self.backbone = backbone_model
        self.classify_layer = tf.keras.layers.Dense(classes,activation='sigmoid')

    def call(self, inputs):
        x = self.backbone.layers[1](inputs)
        x = self.classify_layer(x)
        return x

inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61, 
                backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
model.summary()

它也沒有改變。我很困惑。

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
mobilenet_1.00_224 (Model)   (None, 1000)              4253864   
_________________________________________________________________
dense (Dense)                multiple                  244       
=================================================================
Total params: 4,254,108
Trainable params: 4,232,220
Non-trainable params: 21,888
_________________________________________________________________

但是我發現密集層的參數發生了變化，我不知道發生了什么。

Answer 1

@Ioannis 的答案非常好，但不幸的是它放棄了問題中存在的 keras ' Model Subclassing ' 結構。 如果，就像我一樣，你想保留這個 model 子類並仍然在summary中顯示所有層，你可以使用 for 循環分支到更復雜的 model 的所有單獨層：

class MyMobileNet(tf.keras.Sequential):
    def __init__(self, input_shape=(224, 224, 3), classes=61):
        super(MyMobileNet, self).__init__()
        self.backbone_model = [layer for layer in
               tf.keras.applications.MobileNet(input_shape, include_top=False, pooling='avg').layers]
        self.classificator = tf.keras.layers.Dense(classes,activation='sigmoid', name='classificator')

    def call(self, inputs):
        x = inputs
        for layer in self.backbone_model:
            x = layer(x)
        x = self.classificator(x)
        return x
model = MyMobileNet()

之后我們可以直接構建 model 並調用summary ：

model.build(input_shape=(None, 224, 224, 3))
model.summary()

>
Model: "my_mobile_net"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1_pad (ZeroPadding2D)    (None, 225, 225, 3)       0         
_________________________________________________________________
conv1 (Conv2D)               (None, 112, 112, 32)      864       
_________________________________________________________________
conv1_bn (BatchNormalization (None, 112, 112, 32)      128       
_________________________________________________________________
....
....
conv_pw_13 (Conv2D)          (None, 7, 7, 1024)        1048576   
_________________________________________________________________
conv_pw_13_bn (BatchNormaliz (None, 7, 7, 1024)        4096      
_________________________________________________________________
conv_pw_13_relu (ReLU)       (None, 7, 7, 1024)        0         
_________________________________________________________________
global_average_pooling2d_13  (None, 1024)              0         
_________________________________________________________________
classificator (Dense)        multiple                  62525     
=================================================================
Total params: 3,291,389
Trainable params: 3,269,501
Non-trainable params: 21,888
_________________________________________________________________

Answer 2

為了能夠查看主干層，您必須使用backbone.input輸入和backbone.output .output 構建新的 model

from tensorflow.keras.models import Model
def  Mymodel(backbone_model, classes):
    backbone = backbone_model
    x = backbone.output
    x = tf.keras.layers.Dense(classes,activation='sigmoid')(x)
    model = Model(inputs=backbone.input, outputs=x)
    return model

input_shape = (224, 224, 3)
model = Mymodel(backbone_model=tf.keras.applications.MobileNet(input_shape=input_shape, include_top=False, pooling='avg'),
                classes=61)

model.summary()

Answer 3

您需要為每個 model 調用summary() function 以分別查看其 model 摘要。 請添加backbone_model.summary()以查看移動網絡層的詳細信息。

inputs = tf.keras.Input(shape=(224, 224, 3))
model = Mymodel(inputs=inputs, classes=61, 
            backbone_model=tf.keras.applications.MobileNet())
model.build(input_shape=(20, 224, 224, 3))
backbone_model.summary()
model.summary()

Answer 4

for layer in model.layers:
    layer.summary()

Answer 5

方法摘要中有一個參數 expand_nested。

model.summary(expand_nested=True)