This tutorial is going to show how to load and use a pretrained model from tensorflow library and discusses some techniques to visualize what the networks represent in the selected layers. In addition, we will introduce an interesting work called neural style transfer, using deep learning to compose one image in the style of another image.
import tensorflow as tf
import numpy as np
import time
import functools
import IPython.display as display
from pathlib import Path
import random
from PIL import Image
from matplotlib import pyplot
import matplotlib.pyplot as plt
import matplotlib as mpl
mpl.rcParams['figure.figsize'] = (12,12)
mpl.rcParams['axes.grid'] = False
gpus = tf.config.experimental.list_physical_devices('GPU')
if gpus:
try:
# Restrict TensorFlow to only use the fourth GPU
tf.config.experimental.set_visible_devices(gpus[0], 'GPU')
# Currently, memory growth needs to be the same across GPUs
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
logical_gpus = tf.config.experimental.list_logical_devices('GPU')
print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
except RuntimeError as e:
# Memory growth must be set before GPUs have been initialized
print(e)
2 Physical GPUs, 1 Logical GPUs
Define a function to load an image and limit its maximum dimension to 512 pixels.
def load_img(path_to_img):
max_dim = 512
img = tf.io.read_file(path_to_img)
img = tf.image.decode_image(img, channels=3)
img = tf.image.convert_image_dtype(img, tf.float32)
shape = tf.cast(tf.shape(img)[:-1], tf.float32)
long_dim = max(shape)
scale = max_dim / long_dim
new_shape = tf.cast(shape * scale, tf.int32)
img = tf.image.resize(img, new_shape)
# in order to use CNN, add one additional dimension
# to the original image
# img shape: [height, width, channel] -> [batch_size, height, width, channel]
img = img[tf.newaxis, :]
return img
Create a simple function to display an image:
def imshow(image, title=None):
if len(image.shape) > 3:
image = tf.squeeze(image, axis=0)
plt.imshow(image)
if title:
plt.title(title)
content_path = './dataset/content_nthu.jpg'
content_image = load_img(content_path)
print('Image shape:', content_image.shape)
imshow(content_image, 'Content Image')
Image shape: (1, 341, 512, 3)