We proceed with the recipe as follows:

1. Import the pre-built models and additional modules needed for processing and showing images:

from keras.applications.vgg16 import VGG16
from keras.models import Model
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np

2. Select a specific layer from the network and get the features produced as output:

# pre-built and pre-trained deep learning VGG16 model
base_model = VGG16(weights='imagenet', include_top=True)
for i, layer in enumerate(base_model.layers):
print (i, layer.name, layer.output_shape)
# extract features from block4_pool block
model =
Model(input=base_model.input, output=base_model.get_layer('block4_pool').output)

3. Extract the features for a given image, as in the following code snippet:

img_path = 'cat.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
# get the features from this block
features = model.predict(x)