Python Deep Learning Cookbook

How to do it...

1. Keras has some great tools for using pretrained models. We start with importing the libraries and tools, as follows:

import numpy as npfrom keras.applications.inception_v3 import InceptionV3from keras.applications import imagenet_utilsfrom keras.preprocessing.image import load_imgfrom keras.preprocessing.image import img_to_array

Note that you can replace VGG16 with any of the included pretrained models in Keras.

2. Next, we load the InceptionV3 model as follows:

pretrained_model = InceptionV3model = pretrained_model(weights="imagenet")

3. The InceptionV3 model is trained on the ImageNet dataset, and therefore we should use the same input dimensions if we want to feed the model new images:

input_dim = (299, 299)

4. We will be ...