TensorFlow 1.x Deep Learning Cookbook

How to do it...

We proceed with the recipes as follows:

1. Import numpy for numerical computation, functools to define partial functions with one or more argument already filled in, Pillow for image manipulation, and matplotlib to render images:

import numpy as np from functools import partial import PIL.Image import tensorflow as tf import matplotlib.pyplot as plt

2. Set up the path for the content image and the pretrained model. Start with a seed image that is just random noise:

content_image = 'data/gulli.jpg' # start with a gray image with a little noise img_noise = np.random.uniform(size=(224,224,3)) + 100.0 model_fn = 'data/tensorflow_inception_graph.pb'

3. Load the Inception network downloaded from the internet in a graph. Initialize a ...