Deep Learning with Keras

Utilizing Keras built-in VGG-16 net module

Keras applications are pre-built and pre-trained deep learning models. Weights are downloaded automatically when instantiating a model and stored at ~/.keras/models/. Using built-in code is very easy:

from keras.models import Modelfrom keras.preprocessing import imagefrom keras.optimizers import SGDfrom keras.applications.vgg16 import VGG16import matplotlib.pyplot as pltimport numpy as npimport cv2# prebuild model with pre-trained weights on imagenetmodel = VGG16(weights='imagenet', include_top=True)sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)model.compile(optimizer=sgd, loss='categorical_crossentropy')# resize into VGG16 trained images' formatim = cv2.resize(cv2.imread('steam-locomotive.jpg'), ...