keras ：将层添加到另一个模型

Question

我需要向现有模型添加图层。但是，我需要在“主模型级别”添加层，即我不能使用经典的函数方法。例如，如果我使用类似的东西：

from keras.layers import Dense,Reshape, Input
inp = Input(shape=(15,))
d1 = Dense(224*224*3, activation='linear')(inp)
r1 = Reshape(input_shape)
from keras import Model
model_mod = r1(d1)
model_mod = mobilenet(model_mod)
model_mod = Model(inp, model_mod)

我获得：

Layer (type)                 Output Shape              Param #   
=================================================================
input_5 (InputLayer)         (None, 15)                0         
_________________________________________________________________
dense_4 (Dense)              (None, 150528)            2408448   
_________________________________________________________________
reshape_4 (Reshape)          (None, 224, 224, 3)       0         
_________________________________________________________________
mobilenet_1.00_224 (Model)   (None, 1000)              4253864 

所以，我获得了一个带有嵌套子模型的模型。相反，我会将嵌套子模型的层（mobilenet）“添加”到新的顶层（即在 reshape_4 之后）。我试过：

modelB_input = modelB.input
for layer in modelB.layers:
    if layer == modelB_input:
        continue
    modelA.add(layer)  

它适用于简单的顺序模型（例如，vgg、mobilenet），但对于连接不是严格顺序的更复杂的模型（例如，inception、resnet），此代码并不好。有任何想法吗？

Answer 1

您可以使用keras.layers.Concatenate像这样合并两个模型：

first = Sequential()
first.add(Dense(1, input_shape=(2,), activation='sigmoid'))

second = Sequential()
second.add(Dense(1, input_shape=(1,), activation='sigmoid'))
 
merged = Concatenate([first, second])

（摘自：如何在 keras 中连接两层？）

尽管此示例使用keras.models.Sequential，但它也适用于其他模型或层。

你也可以看看：https : //keras.io/api/layers/merging_layers/concatenate/

Answer 2

如果要在现有模型中将A层添加到B层，可以将B层输出获取到A层，然后通过 解析为新模型tf.keras.model.Model。该方法的全面演示是在用于对象检测或分割的特征提取器中。你可以在这里找到一个

例如，在底部的 VGG16 模型中添加 2 个新层

full_vgg_model = tf.keras.applications.VGG16(
                            include_top=False,
                            weights="imagenet",
                            input_tensor=None,
                            input_shape=None,
                            pooling=None,
                            classes=1000,
                        )

当前层：

Model: "vgg16"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, None, None, 3)]   0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, None, None, 64)    1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, None, None, 64)    36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, None, None, 64)    0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, None, None, 128)   73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, None, None, 128)   147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, None, None, 128)   0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, None, None, 256)   295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, None, None, 256)   590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, None, None, 256)   590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, None, None, 256)   0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, None, None, 512)   1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, None, None, 512)   0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, None, None, 512)   0         
=================================================================
Total params: 14,714,688
Trainable params: 14,714,688
Non-trainable params: 0

然后我添加 2 个新层：

conv6 = tf.keras.layers.Conv2D(1024, 3, strides=(1, 1), padding='same', activation='relu', dilation_rate=(6,6), name='conv6')(full_vgg_model.layers[-1].output)

conv7 = tf.keras.layers.Conv2D(1024, 1, strides=(1, 1), padding='same', activation='relu', name='conv7')(conv6)
    
classification_backbone = tf.keras.Model(
            inputs=full_vgg_model.inputs,
            outputs=[conv6,conv7])

我们把它们堆放在底部！

Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, None, None, 3)]   0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, None, None, 64)    1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, None, None, 64)    36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, None, None, 64)    0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, None, None, 128)   73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, None, None, 128)   147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, None, None, 128)   0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, None, None, 256)   295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, None, None, 256)   590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, None, None, 256)   590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, None, None, 256)   0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, None, None, 512)   1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, None, None, 512)   0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, None, None, 512)   2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, None, None, 512)   0         
_________________________________________________________________
conv6 (Conv2D)               (None, None, None, 1024)  4719616   
_________________________________________________________________
conv7 (Conv2D)               (None, None, None, 1024)  1049600   
=================================================================
Total params: 20,483,904
Trainable params: 20,483,904
Non-trainable params: 0