CODEWITHSUNDEEP
pythonkerasconv-neural-networkkeras-layer
AK_AI
AK_AI

Reputation: 13

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

I am trying to add vgg16 layers to Sequential model but getting the error mentioned in the Question Title 

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())

I am using keras 2.2.4 

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

Upvotes: 1

Views: 6308

Answers (1)

Mitiku
Mitiku

Reputation: 5412

Let's say you want to drop the last layer and add your own last full connected layer with 10, nodes. To achieve this keras functional API can be used.

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())

Or using 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)

You may want to use pretrained weights. You can acheive this by using weights argument

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

You may want to freeze some of layers.

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)

Upvotes: 1

Related Questions