File size: 16,914 Bytes
506da10 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "B8a_URGiowPn"
},
"source": [
"## Overview\n",
"This colab demonstrates the steps to run a family of DeepLab models built by the DeepLab2 library to perform dense pixel labeling tasks. The models used in this colab perform panoptic segmentation, where the predicted value encodes both semantic class and instance label for every pixel (including both ‘thing’ and ‘stuff’ pixels).\n",
"\n",
"### About DeepLab2\n",
"DeepLab2 is a TensorFlow library for deep labeling, aiming to facilitate future research on dense pixel labeling tasks by providing state-of-the-art and easy-to-use TensorFlow models. Code is made publicly available at https://github.com/google-research/deeplab2"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IGVFjkE2o0K8"
},
"source": [
"### Import and helper methods"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dQNiIp-LoV6f"
},
"outputs": [],
"source": [
"import collections\n",
"import os\n",
"import tempfile\n",
"\n",
"from matplotlib import gridspec\n",
"from matplotlib import pyplot as plt\n",
"import numpy as np\n",
"from PIL import Image\n",
"import urllib\n",
"\n",
"import tensorflow as tf\n",
"\n",
"from google.colab import files"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Avk0g2-wo2AO"
},
"outputs": [],
"source": [
"DatasetInfo = collections.namedtuple(\n",
" 'DatasetInfo',\n",
" 'num_classes, label_divisor, thing_list, colormap, class_names')\n",
"\n",
"\n",
"def _cityscapes_label_colormap():\n",
" \"\"\"Creates a label colormap used in CITYSCAPES segmentation benchmark.\n",
"\n",
" See more about CITYSCAPES dataset at https://www.cityscapes-dataset.com/\n",
" M. Cordts, et al. \"The Cityscapes Dataset for Semantic Urban Scene Understanding.\" CVPR. 2016.\n",
"\n",
" Returns:\n",
" A 2-D numpy array with each row being mapped RGB color (in uint8 range).\n",
" \"\"\"\n",
" colormap = np.zeros((256, 3), dtype=np.uint8)\n",
" colormap[0] = [128, 64, 128]\n",
" colormap[1] = [244, 35, 232]\n",
" colormap[2] = [70, 70, 70]\n",
" colormap[3] = [102, 102, 156]\n",
" colormap[4] = [190, 153, 153]\n",
" colormap[5] = [153, 153, 153]\n",
" colormap[6] = [250, 170, 30]\n",
" colormap[7] = [220, 220, 0]\n",
" colormap[8] = [107, 142, 35]\n",
" colormap[9] = [152, 251, 152]\n",
" colormap[10] = [70, 130, 180]\n",
" colormap[11] = [220, 20, 60]\n",
" colormap[12] = [255, 0, 0]\n",
" colormap[13] = [0, 0, 142]\n",
" colormap[14] = [0, 0, 70]\n",
" colormap[15] = [0, 60, 100]\n",
" colormap[16] = [0, 80, 100]\n",
" colormap[17] = [0, 0, 230]\n",
" colormap[18] = [119, 11, 32]\n",
" return colormap\n",
"\n",
"\n",
"def _cityscapes_class_names():\n",
" return ('road', 'sidewalk', 'building', 'wall', 'fence', 'pole',\n",
" 'traffic light', 'traffic sign', 'vegetation', 'terrain', 'sky',\n",
" 'person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',\n",
" 'bicycle')\n",
"\n",
"\n",
"def cityscapes_dataset_information():\n",
" return DatasetInfo(\n",
" num_classes=19,\n",
" label_divisor=1000,\n",
" thing_list=tuple(range(11, 19)),\n",
" colormap=_cityscapes_label_colormap(),\n",
" class_names=_cityscapes_class_names())\n",
"\n",
"\n",
"def perturb_color(color, noise, used_colors, max_trials=50, random_state=None):\n",
" \"\"\"Pertrubs the color with some noise.\n",
"\n",
" If `used_colors` is not None, we will return the color that has\n",
" not appeared before in it.\n",
"\n",
" Args:\n",
" color: A numpy array with three elements [R, G, B].\n",
" noise: Integer, specifying the amount of perturbing noise (in uint8 range).\n",
" used_colors: A set, used to keep track of used colors.\n",
" max_trials: An integer, maximum trials to generate random color.\n",
" random_state: An optional np.random.RandomState. If passed, will be used to\n",
" generate random numbers.\n",
"\n",
" Returns:\n",
" A perturbed color that has not appeared in used_colors.\n",
" \"\"\"\n",
" if random_state is None:\n",
" random_state = np.random\n",
"\n",
" for _ in range(max_trials):\n",
" random_color = color + random_state.randint(\n",
" low=-noise, high=noise + 1, size=3)\n",
" random_color = np.clip(random_color, 0, 255)\n",
"\n",
" if tuple(random_color) not in used_colors:\n",
" used_colors.add(tuple(random_color))\n",
" return random_color\n",
"\n",
" print('Max trial reached and duplicate color will be used. Please consider '\n",
" 'increase noise in `perturb_color()`.')\n",
" return random_color\n",
"\n",
"\n",
"def color_panoptic_map(panoptic_prediction, dataset_info, perturb_noise):\n",
" \"\"\"Helper method to colorize output panoptic map.\n",
"\n",
" Args:\n",
" panoptic_prediction: A 2D numpy array, panoptic prediction from deeplab\n",
" model.\n",
" dataset_info: A DatasetInfo object, dataset associated to the model.\n",
" perturb_noise: Integer, the amount of noise (in uint8 range) added to each\n",
" instance of the same semantic class.\n",
"\n",
" Returns:\n",
" colored_panoptic_map: A 3D numpy array with last dimension of 3, colored\n",
" panoptic prediction map.\n",
" used_colors: A dictionary mapping semantic_ids to a set of colors used\n",
" in `colored_panoptic_map`.\n",
" \"\"\"\n",
" if panoptic_prediction.ndim != 2:\n",
" raise ValueError('Expect 2-D panoptic prediction. Got {}'.format(\n",
" panoptic_prediction.shape))\n",
"\n",
" semantic_map = panoptic_prediction // dataset_info.label_divisor\n",
" instance_map = panoptic_prediction % dataset_info.label_divisor\n",
" height, width = panoptic_prediction.shape\n",
" colored_panoptic_map = np.zeros((height, width, 3), dtype=np.uint8)\n",
"\n",
" used_colors = collections.defaultdict(set)\n",
" # Use a fixed seed to reproduce the same visualization.\n",
" random_state = np.random.RandomState(0)\n",
"\n",
" unique_semantic_ids = np.unique(semantic_map)\n",
" for semantic_id in unique_semantic_ids:\n",
" semantic_mask = semantic_map == semantic_id\n",
" if semantic_id in dataset_info.thing_list:\n",
" # For `thing` class, we will add a small amount of random noise to its\n",
" # correspondingly predefined semantic segmentation colormap.\n",
" unique_instance_ids = np.unique(instance_map[semantic_mask])\n",
" for instance_id in unique_instance_ids:\n",
" instance_mask = np.logical_and(semantic_mask,\n",
" instance_map == instance_id)\n",
" random_color = perturb_color(\n",
" dataset_info.colormap[semantic_id],\n",
" perturb_noise,\n",
" used_colors[semantic_id],\n",
" random_state=random_state)\n",
" colored_panoptic_map[instance_mask] = random_color\n",
" else:\n",
" # For `stuff` class, we use the defined semantic color.\n",
" colored_panoptic_map[semantic_mask] = dataset_info.colormap[semantic_id]\n",
" used_colors[semantic_id].add(tuple(dataset_info.colormap[semantic_id]))\n",
" return colored_panoptic_map, used_colors\n",
"\n",
"\n",
"def vis_segmentation(image,\n",
" panoptic_prediction,\n",
" dataset_info,\n",
" perturb_noise=60):\n",
" \"\"\"Visualizes input image, segmentation map and overlay view.\"\"\"\n",
" plt.figure(figsize=(30, 20))\n",
" grid_spec = gridspec.GridSpec(2, 2)\n",
"\n",
" ax = plt.subplot(grid_spec[0])\n",
" plt.imshow(image)\n",
" plt.axis('off')\n",
" ax.set_title('input image', fontsize=20)\n",
"\n",
" ax = plt.subplot(grid_spec[1])\n",
" panoptic_map, used_colors = color_panoptic_map(panoptic_prediction,\n",
" dataset_info, perturb_noise)\n",
" plt.imshow(panoptic_map)\n",
" plt.axis('off')\n",
" ax.set_title('panoptic map', fontsize=20)\n",
"\n",
" ax = plt.subplot(grid_spec[2])\n",
" plt.imshow(image)\n",
" plt.imshow(panoptic_map, alpha=0.7)\n",
" plt.axis('off')\n",
" ax.set_title('panoptic overlay', fontsize=20)\n",
"\n",
" ax = plt.subplot(grid_spec[3])\n",
" max_num_instances = max(len(color) for color in used_colors.values())\n",
" # RGBA image as legend.\n",
" legend = np.zeros((len(used_colors), max_num_instances, 4), dtype=np.uint8)\n",
" class_names = []\n",
" for i, semantic_id in enumerate(sorted(used_colors)):\n",
" legend[i, :len(used_colors[semantic_id]), :3] = np.array(\n",
" list(used_colors[semantic_id]))\n",
" legend[i, :len(used_colors[semantic_id]), 3] = 255\n",
" if semantic_id \u003c dataset_info.num_classes:\n",
" class_names.append(dataset_info.class_names[semantic_id])\n",
" else:\n",
" class_names.append('ignore')\n",
"\n",
" plt.imshow(legend, interpolation='nearest')\n",
" ax.yaxis.tick_left()\n",
" plt.yticks(range(len(legend)), class_names, fontsize=15)\n",
" plt.xticks([], [])\n",
" ax.tick_params(width=0.0, grid_linewidth=0.0)\n",
" plt.grid('off')\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1ly6p6M2o8SF"
},
"source": [
"### Select a pretrained model"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "peo7LUTtulpQ"
},
"outputs": [],
"source": [
"MODEL_NAME = 'max_deeplab_l_backbone_os16_axial_deeplab_cityscapes_trainfine_saved_model' # @param ['resnet50_os32_panoptic_deeplab_cityscapes_crowd_trainfine_saved_model', 'resnet50_beta_os32_panoptic_deeplab_cityscapes_trainfine_saved_model', 'wide_resnet41_os16_panoptic_deeplab_cityscapes_trainfine_saved_model', 'swidernet_sac_1_1_1_os16_panoptic_deeplab_cityscapes_trainfine_saved_model', 'swidernet_sac_1_1_3_os16_panoptic_deeplab_cityscapes_trainfine_saved_model', 'swidernet_sac_1_1_4.5_os16_panoptic_deeplab_cityscapes_trainfine_saved_model', 'axial_swidernet_1_1_1_os16_axial_deeplab_cityscapes_trainfine_saved_model', 'axial_swidernet_1_1_3_os16_axial_deeplab_cityscapes_trainfine_saved_model', 'axial_swidernet_1_1_4.5_os16_axial_deeplab_cityscapes_trainfine_saved_model', 'max_deeplab_s_backbone_os16_axial_deeplab_cityscapes_trainfine_saved_model', 'max_deeplab_l_backbone_os16_axial_deeplab_cityscapes_trainfine_saved_model']\n",
"\n",
"\n",
"_MODELS = ('resnet50_os32_panoptic_deeplab_cityscapes_crowd_trainfine_saved_model',\n",
" 'resnet50_beta_os32_panoptic_deeplab_cityscapes_trainfine_saved_model',\n",
" 'wide_resnet41_os16_panoptic_deeplab_cityscapes_trainfine_saved_model',\n",
" 'swidernet_sac_1_1_1_os16_panoptic_deeplab_cityscapes_trainfine_saved_model',\n",
" 'swidernet_sac_1_1_3_os16_panoptic_deeplab_cityscapes_trainfine_saved_model',\n",
" 'swidernet_sac_1_1_4.5_os16_panoptic_deeplab_cityscapes_trainfine_saved_model',\n",
" 'axial_swidernet_1_1_1_os16_axial_deeplab_cityscapes_trainfine_saved_model',\n",
" 'axial_swidernet_1_1_3_os16_axial_deeplab_cityscapes_trainfine_saved_model',\n",
" 'axial_swidernet_1_1_4.5_os16_axial_deeplab_cityscapes_trainfine_saved_model',\n",
" 'max_deeplab_s_backbone_os16_axial_deeplab_cityscapes_trainfine_saved_model',\n",
" 'max_deeplab_l_backbone_os16_axial_deeplab_cityscapes_trainfine_saved_model')\n",
"_DOWNLOAD_URL_PATTERN = 'https://storage.googleapis.com/gresearch/tf-deeplab/saved_model/%s.tar.gz'\n",
"\n",
"_MODEL_NAME_TO_URL_AND_DATASET = {\n",
" model: (_DOWNLOAD_URL_PATTERN % model, cityscapes_dataset_information())\n",
" for model in _MODELS\n",
"}\n",
"\n",
"MODEL_URL, DATASET_INFO = _MODEL_NAME_TO_URL_AND_DATASET[MODEL_NAME]\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UjYwP1Sjo4dd"
},
"outputs": [],
"source": [
"model_dir = tempfile.mkdtemp()\n",
"\n",
"download_path = os.path.join(model_dir, MODEL_NAME + '.gz')\n",
"urllib.request.urlretrieve(MODEL_URL, download_path)\n",
"\n",
"!tar -xzvf {download_path} -C {model_dir}\n",
"\n",
"LOADED_MODEL = tf.saved_model.load(os.path.join(model_dir, MODEL_NAME))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "umpwnn4etG6z"
},
"source": [
"### Run on sample images"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "6552FXlAOHnX"
},
"outputs": [],
"source": [
"# Optional, upload an image from your local machine.\n",
"\n",
"uploaded = files.upload()\n",
"\n",
"if not uploaded:\n",
" UPLOADED_FILE = ''\n",
"elif len(uploaded) == 1:\n",
" UPLOADED_FILE = list(uploaded.keys())[0]\n",
"else:\n",
" raise AssertionError('Please upload one image at a time')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "SF40dAWFPZmN"
},
"outputs": [],
"source": [
"# Using provided sample image if no file is uploaded.\n",
"\n",
"if not UPLOADED_FILE:\n",
" # Default image from Mapillary dataset samples (https://www.mapillary.com/dataset/vistas).\n",
" # Neuhold, Gerhard, et al. \"The mapillary vistas dataset for semantic understanding of street scenes.\" ICCV. 2017.\n",
" image_dir = tempfile.mkdtemp()\n",
" download_path = os.path.join(image_dir, 'MVD_research_samples.zip')\n",
" urllib.request.urlretrieve(\n",
" 'https://static.mapillary.com/MVD_research_samples.zip', download_path)\n",
"\n",
" !unzip {download_path} -d {image_dir}\n",
" UPLOADED_FILE = os.path.join(image_dir, 'Asia/tlxGlVwxyGUdUBfkjy1UOQ.jpg')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "bsQ7Oj7jtHDz"
},
"outputs": [],
"source": [
"with tf.io.gfile.GFile(UPLOADED_FILE, 'rb') as f:\n",
" im = np.array(Image.open(f))\n",
"\n",
"output = LOADED_MODEL(tf.cast(im, tf.uint8))\n",
"vis_segmentation(im, output['panoptic_pred'][0], DATASET_INFO)"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [],
"name": "DeepLab_Demo.ipynb",
"private_outputs": true,
"provenance": [
{
"file_id": "18PFmyE_Tcs97fX892SHgtvxaCa0QXTta",
"timestamp": 1623189153618
}
]
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|