How to correctly use an intermediate layer of a vgg model

debugcn 投稿 Dev

willz

What I did is:

from keras.applications.vgg16 import VGG16
from keras.layers import *
from keras.models import Model
import numpy as np 

vgg_model = VGG16(weights='imagenet', include_top=False, input_shape = (224,224, 3)) 

block5_conv3 = vgg_model.get_layer("block5_conv3").output

input_image = Input(shape=(224,224, 3), name='image_input')
vgg_out = vgg_model(input_image)

f0 = Flatten()(block5_conv3)

test_model = Model(inputs=input_image, outputs=f0)
print(test_model.summary())

But I got the following error message:

Traceback (most recent call last):
  File "test.py", line 15, in <module>
    test_model = Model(inputs=input_image, outputs=f0)
  File "C:\Users\wzhou\AppData\Local\Continuum\Anaconda2\envs\tensorflow\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\wzhou\AppData\Local\Continuum\Anaconda2\envs\tensorflow\lib\site-packages\keras\engine\network.py", line 93, in __init__
    self._init_graph_network(*args, **kwargs)
  File "C:\Users\wzhou\AppData\Local\Continuum\Anaconda2\envs\tensorflow\lib\site-packages\keras\engine\network.py", line 237, in _init_graph_network
    self.inputs, self.outputs)
  File "C:\Users\wzhou\AppData\Local\Continuum\Anaconda2\envs\tensorflow\lib\site-packages\keras\engine\network.py", line 1430, in _map_graph_network
    str(layers_with_complete_input))
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_1:0", shape=(?, 224, 224, 3), dtype=float32) at layer "input_1". The following previous layers were accessed without issue: []

I feel something is wrong with the way that I did it but couldn't figure out the right way.

today

There is no need to define an Input layer in this case. You can use the input property of VGG model:

vgg_model = VGG16(weights='imagenet', include_top=False, input_shape = (224,224, 3)) 

block5_conv3 = vgg_model.get_layer("block5_conv3").output
f0 = Flatten()(block5_conv3)

test_model = Model(inputs=vgg_model.input, outputs=f0)

Alternatively, you can define and use a backend function:

from keras import backend as K

# ... (use the code above except the last line)

func = K.function([vgg_model.input], [f0])

# to call it:
outputs = func([your_image_arrays])

この記事はインターネットから収集されたものであり、転載の際にはソースを示してください。

侵害の場合は、連絡してください[email protected]