 Voir sur TensorFlow.org |  Exécuter dans Google Colab |  Voir sur GitHub |  Télécharger le cahier |  Voir le modèle TF Hub |
Basé sur le code du modèle en magenta et la publication:
Explorer la structure d'un temps réel, le réseau de stylisation artistique neurale arbitraire . Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens, Actes de la Conférence britannique Vision (BMVC), 2017.
Installer
Commençons par importer TF2 et toutes les dépendances pertinentes.
import functools
import os
from matplotlib import gridspec
import matplotlib.pylab as plt
import numpy as np
import tensorflow as tf
import tensorflow_hub as hub
print("TF Version: ", tf.__version__)
print("TF Hub version: ", hub.__version__)
print("Eager mode enabled: ", tf.executing_eagerly())
print("GPU available: ", tf.config.list_physical_devices('GPU'))
TF Version: 2.7.0 TF Hub version: 0.12.0 Eager mode enabled: True GPU available: [PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
# @title Define image loading and visualization functions { display-mode: "form" }
def crop_center(image):
"""Returns a cropped square image."""
shape = image.shape
new_shape = min(shape[1], shape[2])
offset_y = max(shape[1] - shape[2], 0) // 2
offset_x = max(shape[2] - shape[1], 0) // 2
image = tf.image.crop_to_bounding_box(
image, offset_y, offset_x, new_shape, new_shape)
return image
@functools.lru_cache(maxsize=None)
def load_image(image_url, image_size=(256, 256), preserve_aspect_ratio=True):
"""Loads and preprocesses images."""
# Cache image file locally.
image_path = tf.keras.utils.get_file(os.path.basename(image_url)[-128:], image_url)
# Load and convert to float32 numpy array, add batch dimension, and normalize to range [0, 1].
img = tf.io.decode_image(
tf.io.read_file(image_path),
channels=3, dtype=tf.float32)[tf.newaxis, ...]
img = crop_center(img)
img = tf.image.resize(img, image_size, preserve_aspect_ratio=True)
return img
def show_n(images, titles=('',)):
n = len(images)
image_sizes = [image.shape[1] for image in images]
w = (image_sizes[0] * 6) // 320
plt.figure(figsize=(w * n, w))
gs = gridspec.GridSpec(1, n, width_ratios=image_sizes)
for i in range(n):
plt.subplot(gs[i])
plt.imshow(images[i][0], aspect='equal')
plt.axis('off')
plt.title(titles[i] if len(titles) > i else '')
plt.show()
Prenons aussi quelques images pour jouer avec.
# @title Load example images { display-mode: "form" }
content_image_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/f/fd/Golden_Gate_Bridge_from_Battery_Spencer.jpg/640px-Golden_Gate_Bridge_from_Battery_Spencer.jpg' # @param {type:"string"}
style_image_url = 'https://upload.wikimedia.org/wikipedia/commons/0/0a/The_Great_Wave_off_Kanagawa.jpg' # @param {type:"string"}
output_image_size = 384 # @param {type:"integer"}
# The content image size can be arbitrary.
content_img_size = (output_image_size, output_image_size)
# The style prediction model was trained with image size 256 and it's the
# recommended image size for the style image (though, other sizes work as
# well but will lead to different results).
style_img_size = (256, 256) # Recommended to keep it at 256.
content_image = load_image(content_image_url, content_img_size)
style_image = load_image(style_image_url, style_img_size)
style_image = tf.nn.avg_pool(style_image, ksize=[3,3], strides=[1,1], padding='SAME')
show_n([content_image, style_image], ['Content image', 'Style image'])
Downloading data from https://upload.wikimedia.org/wikipedia/commons/thumb/f/fd/Golden_Gate_Bridge_from_Battery_Spencer.jpg/640px-Golden_Gate_Bridge_from_Battery_Spencer.jpg 65536/58102 [=================================] - 0s 1us/step 73728/58102 [======================================] - 0s 1us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/0/0a/The_Great_Wave_off_Kanagawa.jpg 2686976/2684586 [==============================] - 0s 0us/step 2695168/2684586 [==============================] - 0s 0us/step
Importer le module TF Hub
# Load TF Hub module.
hub_handle = 'https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2'
hub_module = hub.load(hub_handle)
La signature de ce module hub de stylisation d'images est :
outputs = hub_module(content_image, style_image)
stylized_image = outputs[0]
Où content_image , style_image et stylized_image devraient être 4-D tenseurs avec des formes [batch_size, image_height, image_width, 3] .
Dans l'exemple actuel, nous ne fournissons que des images uniques et la dimension du lot est donc 1, mais on peut utiliser le même module pour traiter plusieurs images en même temps.
Les valeurs d'entrée et de sortie des images doivent être comprises dans la plage [0, 1].
Les formes du contenu et de l'image de style ne doivent pas nécessairement correspondre. La forme de l'image de sortie est la même que la forme de l'image du contenu.
Démontrer la stylisation d'images
# Stylize content image with given style image.
# This is pretty fast within a few milliseconds on a GPU.
outputs = hub_module(tf.constant(content_image), tf.constant(style_image))
stylized_image = outputs[0]
# Visualize input images and the generated stylized image.
show_n([content_image, style_image, stylized_image], titles=['Original content image', 'Style image', 'Stylized image'])
Essayons sur plus d'images
# @title To Run: Load more images { display-mode: "form" }
content_urls = dict(
sea_turtle='https://upload.wikimedia.org/wikipedia/commons/d/d7/Green_Sea_Turtle_grazing_seagrass.jpg',
tuebingen='https://upload.wikimedia.org/wikipedia/commons/0/00/Tuebingen_Neckarfront.jpg',
grace_hopper='https://storage.googleapis.com/download.tensorflow.org/example_images/grace_hopper.jpg',
)
style_urls = dict(
kanagawa_great_wave='https://upload.wikimedia.org/wikipedia/commons/0/0a/The_Great_Wave_off_Kanagawa.jpg',
kandinsky_composition_7='https://upload.wikimedia.org/wikipedia/commons/b/b4/Vassily_Kandinsky%2C_1913_-_Composition_7.jpg',
hubble_pillars_of_creation='https://upload.wikimedia.org/wikipedia/commons/6/68/Pillars_of_creation_2014_HST_WFC3-UVIS_full-res_denoised.jpg',
van_gogh_starry_night='https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg/1024px-Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg',
turner_nantes='https://upload.wikimedia.org/wikipedia/commons/b/b7/JMW_Turner_-_Nantes_from_the_Ile_Feydeau.jpg',
munch_scream='https://upload.wikimedia.org/wikipedia/commons/c/c5/Edvard_Munch%2C_1893%2C_The_Scream%2C_oil%2C_tempera_and_pastel_on_cardboard%2C_91_x_73_cm%2C_National_Gallery_of_Norway.jpg',
picasso_demoiselles_avignon='https://upload.wikimedia.org/wikipedia/en/4/4c/Les_Demoiselles_d%27Avignon.jpg',
picasso_violin='https://upload.wikimedia.org/wikipedia/en/3/3c/Pablo_Picasso%2C_1911-12%2C_Violon_%28Violin%29%2C_oil_on_canvas%2C_Kr%C3%B6ller-M%C3%BCller_Museum%2C_Otterlo%2C_Netherlands.jpg',
picasso_bottle_of_rum='https://upload.wikimedia.org/wikipedia/en/7/7f/Pablo_Picasso%2C_1911%2C_Still_Life_with_a_Bottle_of_Rum%2C_oil_on_canvas%2C_61.3_x_50.5_cm%2C_Metropolitan_Museum_of_Art%2C_New_York.jpg',
fire='https://upload.wikimedia.org/wikipedia/commons/3/36/Large_bonfire.jpg',
derkovits_woman_head='https://upload.wikimedia.org/wikipedia/commons/0/0d/Derkovits_Gyula_Woman_head_1922.jpg',
amadeo_style_life='https://upload.wikimedia.org/wikipedia/commons/8/8e/Untitled_%28Still_life%29_%281913%29_-_Amadeo_Souza-Cardoso_%281887-1918%29_%2817385824283%29.jpg',
derkovtis_talig='https://upload.wikimedia.org/wikipedia/commons/3/37/Derkovits_Gyula_Talig%C3%A1s_1920.jpg',
amadeo_cardoso='https://upload.wikimedia.org/wikipedia/commons/7/7d/Amadeo_de_Souza-Cardoso%2C_1915_-_Landscape_with_black_figure.jpg'
)
content_image_size = 384
style_image_size = 256
content_images = {k: load_image(v, (content_image_size, content_image_size)) for k, v in content_urls.items()}
style_images = {k: load_image(v, (style_image_size, style_image_size)) for k, v in style_urls.items()}
style_images = {k: tf.nn.avg_pool(style_image, ksize=[3,3], strides=[1,1], padding='SAME') for k, style_image in style_images.items()}
Downloading data from https://upload.wikimedia.org/wikipedia/commons/d/d7/Green_Sea_Turtle_grazing_seagrass.jpg 3178496/3170828 [==============================] - 0s 0us/step 3186688/3170828 [==============================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/0/00/Tuebingen_Neckarfront.jpg 409600/406531 [==============================] - 0s 0us/step 417792/406531 [==============================] - 0s 0us/step Downloading data from https://storage.googleapis.com/download.tensorflow.org/example_images/grace_hopper.jpg 65536/61306 [================================] - 0s 0us/step 73728/61306 [====================================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/b/b4/Vassily_Kandinsky%2C_1913_-_Composition_7.jpg 196608/195196 [==============================] - 0s 1us/step 204800/195196 [===============================] - 0s 1us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/6/68/Pillars_of_creation_2014_HST_WFC3-UVIS_full-res_denoised.jpg 46931968/46930988 [==============================] - 2s 0us/step 46940160/46930988 [==============================] - 2s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg/1024px-Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg 401408/396423 [==============================] - 0s 0us/step 409600/396423 [==============================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/b/b7/JMW_Turner_-_Nantes_from_the_Ile_Feydeau.jpg 147456/144340 [==============================] - 0s 1us/step 155648/144340 [================================] - 0s 1us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/c/c5/Edvard_Munch%2C_1893%2C_The_Scream%2C_oil%2C_tempera_and_pastel_on_cardboard%2C_91_x_73_cm%2C_National_Gallery_of_Norway.jpg 11403264/11403121 [==============================] - 1s 0us/step 11411456/11403121 [==============================] - 1s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/en/4/4c/Les_Demoiselles_d%27Avignon.jpg 2908160/2905099 [==============================] - 0s 0us/step 2916352/2905099 [==============================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/en/3/3c/Pablo_Picasso%2C_1911-12%2C_Violon_%28Violin%29%2C_oil_on_canvas%2C_Kr%C3%B6ller-M%C3%BCller_Museum%2C_Otterlo%2C_Netherlands.jpg 1236992/1234199 [==============================] - 0s 0us/step 1245184/1234199 [==============================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/en/7/7f/Pablo_Picasso%2C_1911%2C_Still_Life_with_a_Bottle_of_Rum%2C_oil_on_canvas%2C_61.3_x_50.5_cm%2C_Metropolitan_Museum_of_Art%2C_New_York.jpg 122880/120288 [==============================] - 0s 1us/step 131072/120288 [================================] - 0s 1us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/3/36/Large_bonfire.jpg 139264/131604 [===============================] - 0s 1us/step 147456/131604 [=================================] - 0s 1us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/0/0d/Derkovits_Gyula_Woman_head_1922.jpg 32768/32390 [==============================] - 0s 0us/step 40960/32390 [=====================================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/8/8e/Untitled_%28Still_life%29_%281913%29_-_Amadeo_Souza-Cardoso_%281887-1918%29_%2817385824283%29.jpg 1916928/1914618 [==============================] - 0s 0us/step 1925120/1914618 [==============================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/3/37/Derkovits_Gyula_Talig%C3%A1s_1920.jpg 40960/40620 [==============================] - 0s 0us/step 49152/40620 [====================================] - 0s 0us/step Downloading data from https://upload.wikimedia.org/wikipedia/commons/7/7d/Amadeo_de_Souza-Cardoso%2C_1915_-_Landscape_with_black_figure.jpg 73728/66306 [=================================] - 0s 1us/step 81920/66306 [=====================================] - 0s 1us/step
Spécifiez l'image du contenu principal et le style que vous souhaitez utiliser.
content_name = 'sea_turtle' # @param ['sea_turtle', 'tuebingen', 'grace_hopper']
style_name = 'munch_scream' # @param ['kanagawa_great_wave', 'kandinsky_composition_7', 'hubble_pillars_of_creation', 'van_gogh_starry_night', 'turner_nantes', 'munch_scream', 'picasso_demoiselles_avignon', 'picasso_violin', 'picasso_bottle_of_rum', 'fire', 'derkovits_woman_head', 'amadeo_style_life', 'derkovtis_talig', 'amadeo_cardoso']
stylized_image = hub_module(tf.constant(content_images[content_name]),
tf.constant(style_images[style_name]))[0]
show_n([content_images[content_name], style_images[style_name], stylized_image],
titles=['Original content image', 'Style image', 'Stylized image'])
