TypeError: The added layer must be an instance of class Layer. Found: <keras.engine.input_layer.InputLayer object at 0x7fc6f1b92240>

Question

我正在尝试将 vgg16 层添加到顺序模型，但收到问题标题中提到的错误

from keras.applications.vgg16 import VGG16

from tensorflow.contrib.keras.api.keras.models import Sequential
vgg_model = VGG16()
model = Sequential()
#print(model.summary())
for layer in vgg_model.layers:
        model.add(layer)

print(model.summary())

我正在使用 keras 2.2.4

TypeError: The added layer must be an instance of class Layer. Found: <keras.engine.input_layer.InputLayer object at 0x7fc6f1b92240>

Answer 1

假设您要删除最后一层并添加您自己的最后一个具有 10, 个节点的全连接层。要实现此 keras 功能，可以使用 API。

from tensorflow.contrib.keras.api.keras.models import Sequential
import keras
from keras_applications.vgg16 import VGG16
vgg_model = VGG16()

# replace the last layer with new layer with 10 nodes.
last_layer = vgg_model.layers[-2].output ## 
output = keras.layers.Dense(10, activation="softmax")(last_layer) 

model = keras.models.Model(inputs=vgg_model.inputs, outputs=output)
model.summary()


print(model.summary())

或使用 include_top = False

vgg_model = VGG16(include_top=False)
vgg_output = vgg_model.outputs[0]
output = keras.layers.Dense(10, activation="softmax")(vgg_output)

model = keras.models.Model(inputs=vgg_model.inputs, outputs=output)

您可能想要使用预训练权重。您可以通过使用权重参数

来实现这一点

vgg_model = VGG16(weights='imagenet',include_top=False)

您可能想要冻结一些图层。

number_of_layers_to_freeze = 10
vgg_model = VGG16(include_top=False)
for i in range(number_of_layers_to_freeze):
    vgg_model.layers[i].trainable = False
vgg_output = vgg_model.outputs[0]
output = keras.layers.Dense(10, activation="softmax")(vgg_output)

model = keras.models.Model(inputs=vgg_model.inputs, outputs=output)

TypeError: The added layer must be an instance of class Layer. Found: <keras.engine.input_layer.InputLayer object at 0x7fc6f1b92240>

TypeError: The added layer must be an instance of class Layer. Found: <keras.engine.input_layer.InputLayer object at 0x7fc6f1b92240>

python

conv-neural-network

keras

keras-layer