File size: 14,202 Bytes
97b6013 |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "KFPcBuVFw61h"
},
"source": [
"# Overview\n",
"\n",
"This colab demonstrates the steps to use the DeepLab model to perform semantic segmentation on a sample input image. Expected outputs are semantic labels overlayed on the sample image.\n",
"\n",
"### About DeepLab\n",
"The models used in this colab perform semantic segmentation. Semantic segmentation models focus on assigning semantic labels, such as sky, person, or car, to multiple objects and stuff in a single image."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "t3ozFsEEP-u_"
},
"source": [
"# Instructions\n",
"\u003ch3\u003e\u003ca href=\"https://cloud.google.com/tpu/\"\u003e\u003cimg valign=\"middle\" src=\"https://raw.githubusercontent.com/GoogleCloudPlatform/tensorflow-without-a-phd/master/tensorflow-rl-pong/images/tpu-hexagon.png\" width=\"50\"\u003e\u003c/a\u003e \u0026nbsp;\u0026nbsp;Use a free TPU device\u003c/h3\u003e\n",
"\n",
" 1. On the main menu, click Runtime and select **Change runtime type**. Set \"TPU\" as the hardware accelerator.\n",
" 1. Click Runtime again and select **Runtime \u003e Run All**. You can also run the cells manually with Shift-ENTER."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "7cRiapZ1P3wy"
},
"source": [
"## Import Libraries"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "code",
"colab": {},
"colab_type": "code",
"id": "kAbdmRmvq0Je"
},
"outputs": [],
"source": [
"import os\n",
"from io import BytesIO\n",
"import tarfile\n",
"import tempfile\n",
"from six.moves import urllib\n",
"\n",
"from matplotlib import gridspec\n",
"from matplotlib import pyplot as plt\n",
"import numpy as np\n",
"from PIL import Image\n",
"\n",
"%tensorflow_version 1.x\n",
"import tensorflow as tf"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "p47cYGGOQE1W"
},
"source": [
"## Import helper methods\n",
"These methods help us perform the following tasks:\n",
"* Load the latest version of the pretrained DeepLab model\n",
"* Load the colormap from the PASCAL VOC dataset\n",
"* Adds colors to various labels, such as \"pink\" for people, \"green\" for bicycle and more\n",
"* Visualize an image, and add an overlay of colors on various regions"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "code",
"colab": {},
"colab_type": "code",
"id": "vN0kU6NJ1Ye5"
},
"outputs": [],
"source": [
"class DeepLabModel(object):\n",
" \"\"\"Class to load deeplab model and run inference.\"\"\"\n",
"\n",
" INPUT_TENSOR_NAME = 'ImageTensor:0'\n",
" OUTPUT_TENSOR_NAME = 'SemanticPredictions:0'\n",
" INPUT_SIZE = 513\n",
" FROZEN_GRAPH_NAME = 'frozen_inference_graph'\n",
"\n",
" def __init__(self, tarball_path):\n",
" \"\"\"Creates and loads pretrained deeplab model.\"\"\"\n",
" self.graph = tf.Graph()\n",
"\n",
" graph_def = None\n",
" # Extract frozen graph from tar archive.\n",
" tar_file = tarfile.open(tarball_path)\n",
" for tar_info in tar_file.getmembers():\n",
" if self.FROZEN_GRAPH_NAME in os.path.basename(tar_info.name):\n",
" file_handle = tar_file.extractfile(tar_info)\n",
" graph_def = tf.GraphDef.FromString(file_handle.read())\n",
" break\n",
"\n",
" tar_file.close()\n",
"\n",
" if graph_def is None:\n",
" raise RuntimeError('Cannot find inference graph in tar archive.')\n",
"\n",
" with self.graph.as_default():\n",
" tf.import_graph_def(graph_def, name='')\n",
"\n",
" self.sess = tf.Session(graph=self.graph)\n",
"\n",
" def run(self, image):\n",
" \"\"\"Runs inference on a single image.\n",
"\n",
" Args:\n",
" image: A PIL.Image object, raw input image.\n",
"\n",
" Returns:\n",
" resized_image: RGB image resized from original input image.\n",
" seg_map: Segmentation map of `resized_image`.\n",
" \"\"\"\n",
" width, height = image.size\n",
" resize_ratio = 1.0 * self.INPUT_SIZE / max(width, height)\n",
" target_size = (int(resize_ratio * width), int(resize_ratio * height))\n",
" resized_image = image.convert('RGB').resize(target_size, Image.ANTIALIAS)\n",
" batch_seg_map = self.sess.run(\n",
" self.OUTPUT_TENSOR_NAME,\n",
" feed_dict={self.INPUT_TENSOR_NAME: [np.asarray(resized_image)]})\n",
" seg_map = batch_seg_map[0]\n",
" return resized_image, seg_map\n",
"\n",
"\n",
"def create_pascal_label_colormap():\n",
" \"\"\"Creates a label colormap used in PASCAL VOC segmentation benchmark.\n",
"\n",
" Returns:\n",
" A Colormap for visualizing segmentation results.\n",
" \"\"\"\n",
" colormap = np.zeros((256, 3), dtype=int)\n",
" ind = np.arange(256, dtype=int)\n",
"\n",
" for shift in reversed(range(8)):\n",
" for channel in range(3):\n",
" colormap[:, channel] |= ((ind \u003e\u003e channel) \u0026 1) \u003c\u003c shift\n",
" ind \u003e\u003e= 3\n",
"\n",
" return colormap\n",
"\n",
"\n",
"def label_to_color_image(label):\n",
" \"\"\"Adds color defined by the dataset colormap to the label.\n",
"\n",
" Args:\n",
" label: A 2D array with integer type, storing the segmentation label.\n",
"\n",
" Returns:\n",
" result: A 2D array with floating type. The element of the array\n",
" is the color indexed by the corresponding element in the input label\n",
" to the PASCAL color map.\n",
"\n",
" Raises:\n",
" ValueError: If label is not of rank 2 or its value is larger than color\n",
" map maximum entry.\n",
" \"\"\"\n",
" if label.ndim != 2:\n",
" raise ValueError('Expect 2-D input label')\n",
"\n",
" colormap = create_pascal_label_colormap()\n",
"\n",
" if np.max(label) \u003e= len(colormap):\n",
" raise ValueError('label value too large.')\n",
"\n",
" return colormap[label]\n",
"\n",
"\n",
"def vis_segmentation(image, seg_map):\n",
" \"\"\"Visualizes input image, segmentation map and overlay view.\"\"\"\n",
" plt.figure(figsize=(15, 5))\n",
" grid_spec = gridspec.GridSpec(1, 4, width_ratios=[6, 6, 6, 1])\n",
"\n",
" plt.subplot(grid_spec[0])\n",
" plt.imshow(image)\n",
" plt.axis('off')\n",
" plt.title('input image')\n",
"\n",
" plt.subplot(grid_spec[1])\n",
" seg_image = label_to_color_image(seg_map).astype(np.uint8)\n",
" plt.imshow(seg_image)\n",
" plt.axis('off')\n",
" plt.title('segmentation map')\n",
"\n",
" plt.subplot(grid_spec[2])\n",
" plt.imshow(image)\n",
" plt.imshow(seg_image, alpha=0.7)\n",
" plt.axis('off')\n",
" plt.title('segmentation overlay')\n",
"\n",
" unique_labels = np.unique(seg_map)\n",
" ax = plt.subplot(grid_spec[3])\n",
" plt.imshow(\n",
" FULL_COLOR_MAP[unique_labels].astype(np.uint8), interpolation='nearest')\n",
" ax.yaxis.tick_right()\n",
" plt.yticks(range(len(unique_labels)), LABEL_NAMES[unique_labels])\n",
" plt.xticks([], [])\n",
" ax.tick_params(width=0.0)\n",
" plt.grid('off')\n",
" plt.show()\n",
"\n",
"\n",
"LABEL_NAMES = np.asarray([\n",
" 'background', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',\n",
" 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike',\n",
" 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tv'\n",
"])\n",
"\n",
"FULL_LABEL_MAP = np.arange(len(LABEL_NAMES)).reshape(len(LABEL_NAMES), 1)\n",
"FULL_COLOR_MAP = label_to_color_image(FULL_LABEL_MAP)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "nGcZzNkASG9A"
},
"source": [
"## Select a pretrained model\n",
"We have trained the DeepLab model using various backbone networks. Select one from the MODEL_NAME list."
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab": {},
"colab_type": "code",
"id": "c4oXKmnjw6i_"
},
"outputs": [],
"source": [
"MODEL_NAME = 'mobilenetv2_coco_voctrainaug' # @param ['mobilenetv2_coco_voctrainaug', 'mobilenetv2_coco_voctrainval', 'xception_coco_voctrainaug', 'xception_coco_voctrainval']\n",
"\n",
"_DOWNLOAD_URL_PREFIX = 'http://download.tensorflow.org/models/'\n",
"_MODEL_URLS = {\n",
" 'mobilenetv2_coco_voctrainaug':\n",
" 'deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz',\n",
" 'mobilenetv2_coco_voctrainval':\n",
" 'deeplabv3_mnv2_pascal_trainval_2018_01_29.tar.gz',\n",
" 'xception_coco_voctrainaug':\n",
" 'deeplabv3_pascal_train_aug_2018_01_04.tar.gz',\n",
" 'xception_coco_voctrainval':\n",
" 'deeplabv3_pascal_trainval_2018_01_04.tar.gz',\n",
"}\n",
"_TARBALL_NAME = 'deeplab_model.tar.gz'\n",
"\n",
"model_dir = tempfile.mkdtemp()\n",
"tf.gfile.MakeDirs(model_dir)\n",
"\n",
"download_path = os.path.join(model_dir, _TARBALL_NAME)\n",
"print('downloading model, this might take a while...')\n",
"urllib.request.urlretrieve(_DOWNLOAD_URL_PREFIX + _MODEL_URLS[MODEL_NAME],\n",
" download_path)\n",
"print('download completed! loading DeepLab model...')\n",
"\n",
"MODEL = DeepLabModel(download_path)\n",
"print('model loaded successfully!')"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "SZst78N-4OKO"
},
"source": [
"## Run on sample images\n",
"\n",
"Select one of sample images (leave `IMAGE_URL` empty) or feed any internet image\n",
"url for inference.\n",
"\n",
"Note that this colab uses single scale inference for fast computation,\n",
"so the results may slightly differ from the visualizations in the\n",
"[README](https://github.com/tensorflow/models/blob/master/research/deeplab/README.md) file,\n",
"which uses multi-scale and left-right flipped inputs."
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "form",
"colab": {},
"colab_type": "code",
"id": "edGukUHXyymr"
},
"outputs": [],
"source": [
"\n",
"SAMPLE_IMAGE = 'image1' # @param ['image1', 'image2', 'image3']\n",
"IMAGE_URL = '' #@param {type:\"string\"}\n",
"\n",
"_SAMPLE_URL = ('https://github.com/tensorflow/models/blob/master/research/'\n",
" 'deeplab/g3doc/img/%s.jpg?raw=true')\n",
"\n",
"\n",
"def run_visualization(url):\n",
" \"\"\"Inferences DeepLab model and visualizes result.\"\"\"\n",
" try:\n",
" f = urllib.request.urlopen(url)\n",
" jpeg_str = f.read()\n",
" original_im = Image.open(BytesIO(jpeg_str))\n",
" except IOError:\n",
" print('Cannot retrieve image. Please check url: ' + url)\n",
" return\n",
"\n",
" print('running deeplab on image %s...' % url)\n",
" resized_im, seg_map = MODEL.run(original_im)\n",
"\n",
" vis_segmentation(resized_im, seg_map)\n",
"\n",
"\n",
"image_url = IMAGE_URL or _SAMPLE_URL % SAMPLE_IMAGE\n",
"run_visualization(image_url)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "aUbVoHScTJYe"
},
"source": [
"## What's next\n",
"\n",
"* Learn about [Cloud TPUs](https://cloud.google.com/tpu/docs) that Google designed and optimized specifically to speed up and scale up ML workloads for training and inference and to enable ML engineers and researchers to iterate more quickly.\n",
"* Explore the range of [Cloud TPU tutorials and Colabs](https://cloud.google.com/tpu/docs/tutorials) to find other examples that can be used when implementing your ML project.\n",
"* For more information on running the DeepLab model on Cloud TPUs, see the [DeepLab tutorial](https://cloud.google.com/tpu/docs/tutorials/deeplab).\n"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [],
"name": "DeepLab Demo.ipynb",
"provenance": [],
"toc_visible": true,
"version": "0.3.2"
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|