Spaces:
Running
Running
File size: 16,053 Bytes
46b5e1b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "ScitaPqhKtuW"
},
"source": [
"##### Copyright 2019 The TensorFlow Hub Authors.\n",
"\n",
"Licensed under the Apache License, Version 2.0 (the \"License\");"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "jvztxQ6VsK2k"
},
"outputs": [],
"source": [
"# Copyright 2019 The TensorFlow Hub Authors. All Rights Reserved.\n",
"#\n",
"# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"# you may not use this file except in compliance with the License.\n",
"# You may obtain a copy of the License at\n",
"#\n",
"# http://www.apache.org/licenses/LICENSE-2.0\n",
"#\n",
"# Unless required by applicable law or agreed to in writing, software\n",
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"# See the License for the specific language governing permissions and\n",
"# limitations under the License.\n",
"# =============================================================================="
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "oXlcl8lqBgAD"
},
"source": [
"# Fast Style Transfer for Arbitrary Styles\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MfBg1C5NB3X0"
},
"source": [
"<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://www.tensorflow.org/hub/tutorials/tf2_arbitrary_image_stylization\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/tf2_arbitrary_image_stylization.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/hub/blob/master/examples/colab/tf2_arbitrary_image_stylization.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View on GitHub</a>\n",
" </td>\n",
" <td>\n",
" <a href=\"https://storage.googleapis.com/tensorflow_docs/hub/examples/colab/tf2_arbitrary_image_stylization.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
" </td>\n",
" <td>\n",
" <a href=\"https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2\"><img src=\"https://www.tensorflow.org/images/hub_logo_32px.png\" />See TF Hub model</a>\n",
" </td>\n",
"</table>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YeeuYzbZcJzs"
},
"source": [
"Based on the model code in [magenta](https://github.com/tensorflow/magenta/tree/master/magenta/models/arbitrary_image_stylization) and the publication:\n",
"\n",
"[Exploring the structure of a real-time, arbitrary neural artistic stylization\n",
"network](https://arxiv.org/abs/1705.06830).\n",
"*Golnaz Ghiasi, Honglak Lee,\n",
"Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens*,\n",
"Proceedings of the British Machine Vision Conference (BMVC), 2017.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "TaM8BVxrCA2E"
},
"source": [
"## Setup"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "J65jog2ncJzt"
},
"source": [
"Let's start with importing TF2 and all relevant dependencies."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "v-KXRY5XBu2u"
},
"outputs": [],
"source": [
"import functools\n",
"import os\n",
"\n",
"from matplotlib import gridspec\n",
"import matplotlib.pylab as plt\n",
"import numpy as np\n",
"import tensorflow as tf\n",
"import tensorflow_hub as hub\n",
"\n",
"print(\"TF Version: \", tf.__version__)\n",
"print(\"TF Hub version: \", hub.__version__)\n",
"print(\"Eager mode enabled: \", tf.executing_eagerly())\n",
"print(\"GPU available: \", tf.config.list_physical_devices('GPU'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "tsoDv_9geoZn"
},
"outputs": [],
"source": [
"# @title Define image loading and visualization functions { display-mode: \"form\" }\n",
"\n",
"def crop_center(image):\n",
" \"\"\"Returns a cropped square image.\"\"\"\n",
" shape = image.shape\n",
" new_shape = min(shape[1], shape[2])\n",
" offset_y = max(shape[1] - shape[2], 0) // 2\n",
" offset_x = max(shape[2] - shape[1], 0) // 2\n",
" image = tf.image.crop_to_bounding_box(\n",
" image, offset_y, offset_x, new_shape, new_shape)\n",
" return image\n",
"\n",
"@functools.lru_cache(maxsize=None)\n",
"def load_image(image_url, image_size=(256, 256), preserve_aspect_ratio=True):\n",
" \"\"\"Loads and preprocesses images.\"\"\"\n",
" # Cache image file locally.\n",
" image_path = tf.keras.utils.get_file(os.path.basename(image_url)[-128:], image_url)\n",
" # Load and convert to float32 numpy array, add batch dimension, and normalize to range [0, 1].\n",
" img = tf.io.decode_image(\n",
" tf.io.read_file(image_path),\n",
" channels=3, dtype=tf.float32)[tf.newaxis, ...]\n",
" img = crop_center(img)\n",
" img = tf.image.resize(img, image_size, preserve_aspect_ratio=True)\n",
" return img\n",
"\n",
"def show_n(images, titles=('',)):\n",
" n = len(images)\n",
" image_sizes = [image.shape[1] for image in images]\n",
" w = (image_sizes[0] * 6) // 320\n",
" plt.figure(figsize=(w * n, w))\n",
" gs = gridspec.GridSpec(1, n, width_ratios=image_sizes)\n",
" for i in range(n):\n",
" plt.subplot(gs[i])\n",
" plt.imshow(images[i][0], aspect='equal')\n",
" plt.axis('off')\n",
" plt.title(titles[i] if len(titles) > i else '')\n",
" plt.show()\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "8etHh05-CJHc"
},
"source": [
"Let's get as well some images to play with."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dRc0vat3Alzo"
},
"outputs": [],
"source": [
"# @title Load example images { display-mode: \"form\" }\n",
"\n",
"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\"}\n",
"style_image_url = 'https://upload.wikimedia.org/wikipedia/commons/0/0a/The_Great_Wave_off_Kanagawa.jpg' # @param {type:\"string\"}\n",
"output_image_size = 384 # @param {type:\"integer\"}\n",
"\n",
"# The content image size can be arbitrary.\n",
"content_img_size = (output_image_size, output_image_size)\n",
"# The style prediction model was trained with image size 256 and it's the \n",
"# recommended image size for the style image (though, other sizes work as \n",
"# well but will lead to different results).\n",
"style_img_size = (256, 256) # Recommended to keep it at 256.\n",
"\n",
"content_image = load_image(content_image_url, content_img_size)\n",
"style_image = load_image(style_image_url, style_img_size)\n",
"style_image = tf.nn.avg_pool(style_image, ksize=[3,3], strides=[1,1], padding='SAME')\n",
"show_n([content_image, style_image], ['Content image', 'Style image'])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yL2Bn5ThR1nY"
},
"source": [
"## Import TF Hub module"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "467AVDSuzBPc"
},
"outputs": [],
"source": [
"# Load TF Hub module.\n",
"\n",
"hub_handle = 'https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2'\n",
"hub_module = hub.load(hub_handle)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uAR70_3wLEDB"
},
"source": [
"The signature of this hub module for image stylization is:\n",
"```\n",
"outputs = hub_module(content_image, style_image)\n",
"stylized_image = outputs[0]\n",
"```\n",
"Where `content_image`, `style_image`, and `stylized_image` are expected to be 4-D Tensors with shapes `[batch_size, image_height, image_width, 3]`.\n",
"\n",
"In the current example we provide only single images and therefore the batch dimension is 1, but one can use the same module to process more images at the same time.\n",
"\n",
"The input and output values of the images should be in the range [0, 1].\n",
"\n",
"The shapes of content and style image don't have to match. Output image shape\n",
"is the same as the content image shape."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qEhYJno1R7rP"
},
"source": [
"## Demonstrate image stylization"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "lnAv-F3O9fLV"
},
"outputs": [],
"source": [
"# Stylize content image with given style image.\n",
"# This is pretty fast within a few milliseconds on a GPU.\n",
"\n",
"outputs = hub_module(tf.constant(content_image), tf.constant(style_image))\n",
"stylized_image = outputs[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "OEAPEdq698gs"
},
"outputs": [],
"source": [
"# Visualize input images and the generated stylized image.\n",
"\n",
"show_n([content_image, style_image, stylized_image], titles=['Original content image', 'Style image', 'Stylized image'])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "v-gYvjTWK-lx"
},
"source": [
"## Let's try it on more images"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "WSMaY0YBNfkK"
},
"outputs": [],
"source": [
"# @title To Run: Load more images { display-mode: \"form\" }\n",
"\n",
"content_urls = dict(\n",
" sea_turtle='https://upload.wikimedia.org/wikipedia/commons/d/d7/Green_Sea_Turtle_grazing_seagrass.jpg',\n",
" tuebingen='https://upload.wikimedia.org/wikipedia/commons/0/00/Tuebingen_Neckarfront.jpg',\n",
" grace_hopper='https://storage.googleapis.com/download.tensorflow.org/example_images/grace_hopper.jpg',\n",
" )\n",
"style_urls = dict(\n",
" kanagawa_great_wave='https://upload.wikimedia.org/wikipedia/commons/0/0a/The_Great_Wave_off_Kanagawa.jpg',\n",
" kandinsky_composition_7='https://upload.wikimedia.org/wikipedia/commons/b/b4/Vassily_Kandinsky%2C_1913_-_Composition_7.jpg',\n",
" hubble_pillars_of_creation='https://upload.wikimedia.org/wikipedia/commons/6/68/Pillars_of_creation_2014_HST_WFC3-UVIS_full-res_denoised.jpg',\n",
" 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',\n",
" turner_nantes='https://upload.wikimedia.org/wikipedia/commons/b/b7/JMW_Turner_-_Nantes_from_the_Ile_Feydeau.jpg',\n",
" 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',\n",
" picasso_demoiselles_avignon='https://upload.wikimedia.org/wikipedia/en/4/4c/Les_Demoiselles_d%27Avignon.jpg',\n",
" 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',\n",
" 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',\n",
" fire='https://upload.wikimedia.org/wikipedia/commons/3/36/Large_bonfire.jpg',\n",
" derkovits_woman_head='https://upload.wikimedia.org/wikipedia/commons/0/0d/Derkovits_Gyula_Woman_head_1922.jpg',\n",
" 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',\n",
" derkovtis_talig='https://upload.wikimedia.org/wikipedia/commons/3/37/Derkovits_Gyula_Talig%C3%A1s_1920.jpg',\n",
" amadeo_cardoso='https://upload.wikimedia.org/wikipedia/commons/7/7d/Amadeo_de_Souza-Cardoso%2C_1915_-_Landscape_with_black_figure.jpg'\n",
")\n",
"\n",
"content_image_size = 384\n",
"style_image_size = 256\n",
"content_images = {k: load_image(v, (content_image_size, content_image_size)) for k, v in content_urls.items()}\n",
"style_images = {k: load_image(v, (style_image_size, style_image_size)) for k, v in style_urls.items()}\n",
"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()}\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dqB6aNTLNVkK"
},
"outputs": [],
"source": [
"#@title Specify the main content image and the style you want to use. { display-mode: \"form\" }\n",
"\n",
"content_name = 'sea_turtle' # @param ['sea_turtle', 'tuebingen', 'grace_hopper']\n",
"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']\n",
"\n",
"stylized_image = hub_module(tf.constant(content_images[content_name]),\n",
" tf.constant(style_images[style_name]))[0]\n",
"\n",
"show_n([content_images[content_name], style_images[style_name], stylized_image],\n",
" titles=['Original content image', 'Style image', 'Stylized image'])"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "TF-Hub: Fast Style Transfer for Arbitrary Styles.ipynb",
"private_outputs": true,
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |