Deep Learning with Keras

Recycling pre-built deep learning models for extracting features

One very simple idea is to use VGG-16 and, more generally, DCNN, for feature extraction. This code implements the idea by extracting features from a specific layer:

from keras.applications.vgg16 import VGG16from keras.models import Modelfrom keras.preprocessing import imagefrom keras.applications.vgg16 import preprocess_inputimport numpy as np# pre-built and pre-trained deep learning VGG16 modelbase_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 blockmodel =Model(input=base_model.input, output=base_model.get_layer('block4_pool').output)img_path = 'cat.jpg' ...