File size: 27,078 Bytes
25e57c6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "uY4QMaQw9Yvi"
},
"source": [
"##### Copyright 2022 The TensorFlow Authors."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "NM0OBLSN9heW"
},
"outputs": [],
"source": [
"#@title 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",
"# https://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."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sg-GchQwFr_r"
},
"source": [
"# Semantic Segmentation with Model Garden\n",
"\n",
"\u003ctable class=\"tfo-notebook-buttons\" align=\"left\"\u003e\n",
" \u003ctd\u003e\n",
" \u003ca target=\"_blank\" href=\"https://www.tensorflow.org/tfmodels/vision/semantic_segmentation\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" /\u003eView on TensorFlow.org\u003c/a\u003e\n",
" \u003c/td\u003e\n",
" \u003ctd\u003e\n",
" \u003ca target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/models/blob/master/docs/vision/semantic_segmentation.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" /\u003eRun in Google Colab\u003c/a\u003e\n",
" \u003c/td\u003e\n",
" \u003ctd\u003e\n",
" \u003ca target=\"_blank\" href=\"https://github.com/tensorflow/models/blob/master/docs/vision/semantic_segmentation.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" /\u003eView on GitHub\u003c/a\u003e\n",
" \u003c/td\u003e\n",
" \u003ctd\u003e\n",
" \u003ca href=\"https://storage.googleapis.com/tensorflow_docs/models/docs/vision/semantic_segmentation.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/download_logo_32px.png\" /\u003eDownload notebook\u003c/a\u003e\n",
" \u003c/td\u003e\n",
"\u003c/table\u003e"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "c6J4IoNfN9jp"
},
"source": [
"This tutorial trains a [DeepLabV3](https://arxiv.org/pdf/1706.05587.pdf) with [Mobilenet V2](https://arxiv.org/abs/1801.04381) as backbone model from the [TensorFlow Model Garden](https://pypi.org/project/tf-models-official/) package (tensorflow-models).\n",
"\n",
"\n",
"[Model Garden](https://www.tensorflow.org/tfmodels) contains a collection of state-of-the-art models, implemented with TensorFlow's high-level APIs. The implementations demonstrate the best practices for modeling, letting users to take full advantage of TensorFlow for their research and product development.\n",
"\n",
"**Dataset**: [Oxford-IIIT Pets](https://www.tensorflow.org/datasets/catalog/oxford_iiit_pet)\n",
"\n",
"* The Oxford-IIIT pet dataset is a 37 category pet image dataset with roughly 200 images for each class. The images have large variations in scale, pose and lighting. All images have an associated ground truth annotation of breed.\n",
"\n",
"\n",
"**This tutorial demonstrates how to:**\n",
"\n",
"1. Use models from the TensorFlow Models package.\n",
"2. Train/Fine-tune a pre-built DeepLabV3 with mobilenet as backbone for Semantic Segmentation.\n",
"3. Export the trained/tuned DeepLabV3 model"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "AlxYhP0XFnDn"
},
"source": [
"## Install necessary dependencies"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "pXWAySwgaWpN"
},
"outputs": [],
"source": [
"!pip install -U -q \"tensorflow\u003e=2.9.2\" \"tf-models-official\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uExUsXlgaPD6"
},
"source": [
"## Import required libraries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mOmKZ3Vky5t9"
},
"outputs": [],
"source": [
"import os\n",
"import pprint\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from IPython import display"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "nF8IHrXua_0b"
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"import tensorflow_datasets as tfds\n",
"\n",
"\n",
"import orbit\n",
"import tensorflow_models as tfm\n",
"from official.vision.data import tfrecord_lib\n",
"from official.vision.serving import export_saved_model_lib\n",
"from official.vision.utils.object_detection import visualization_utils\n",
"\n",
"pp = pprint.PrettyPrinter(indent=4) # Set Pretty Print Indentation\n",
"print(tf.__version__) # Check the version of tensorflow used\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gMs4l2dpaTd3"
},
"source": [
"## Custom dataset preparation for semantic segmentation\n",
"Models in Official repository (of model-garden) require models in a TFRecords dataformat.\n",
"\n",
"Please check [this resource](https://www.tensorflow.org/tutorials/load_data/tfrecord) to learn more about TFRecords data format.\n",
"\n",
"[Oxford_IIIT_pet:3](https://www.tensorflow.org/datasets/catalog/oxford_iiit_pet) dataset is taken from [Tensorflow Datasets](https://www.tensorflow.org/datasets/catalog/overview)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "JpWK1Z-N3fHh"
},
"outputs": [],
"source": [
"(train_ds, val_ds, test_ds), info = tfds.load(\n",
" 'oxford_iiit_pet:3.*.*',\n",
" split=['train+test[:50%]', 'test[50%:80%]', 'test[80%:100%]'],\n",
" with_info=True)\n",
"info"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Sq6s11E1bMJB"
},
"source": [
"### Helper function to encode dataset as tfrecords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "NlEf_C-DjDHG"
},
"outputs": [],
"source": [
"def process_record(record):\n",
" keys_to_features = {\n",
" 'image/encoded': tfrecord_lib.convert_to_feature(\n",
" tf.io.encode_jpeg(record['image']).numpy()),\n",
" 'image/height': tfrecord_lib.convert_to_feature(record['image'].shape[0]),\n",
" 'image/width': tfrecord_lib.convert_to_feature(record['image'].shape[1]),\n",
" 'image/segmentation/class/encoded':tfrecord_lib.convert_to_feature(\n",
" tf.io.encode_png(record['segmentation_mask'] - 1).numpy())\n",
" }\n",
" example = tf.train.Example(\n",
" features=tf.train.Features(feature=keys_to_features))\n",
" return example"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "FoapGlIebP9r"
},
"source": [
"### Write TFRecords to a folder"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dDbMn5q551LQ"
},
"outputs": [],
"source": [
"output_dir = './oxford_iiit_pet_tfrecords/'\n",
"LOG_EVERY = 100\n",
"if not os.path.exists(output_dir):\n",
" os.mkdir(output_dir)\n",
"\n",
"def write_tfrecords(dataset, output_path, num_shards=1):\n",
" writers = [\n",
" tf.io.TFRecordWriter(\n",
" output_path + '-%05d-of-%05d.tfrecord' % (i, num_shards))\n",
" for i in range(num_shards)\n",
" ]\n",
" for idx, record in enumerate(dataset):\n",
" if idx % LOG_EVERY == 0:\n",
" print('On image %d', idx)\n",
" tf_example = process_record(record)\n",
" writers[idx % num_shards].write(tf_example.SerializeToString())"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QHDD-D7rbZj7"
},
"source": [
"### Write training data as TFRecords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "qxJnVUfT0qBJ"
},
"outputs": [],
"source": [
"output_train_tfrecs = output_dir + 'train'\n",
"write_tfrecords(train_ds, output_train_tfrecs, num_shards=10)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ap55RwVFbhtu"
},
"source": [
"### Write validation data as TFRecords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Fgq-VxF79ucR"
},
"outputs": [],
"source": [
"output_val_tfrecs = output_dir + 'val'\n",
"write_tfrecords(val_ds, output_val_tfrecs, num_shards=5)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0AZoIEzRbxZu"
},
"source": [
"### Write test data as TFRecords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QmwFmbP69t0U"
},
"outputs": [],
"source": [
"output_test_tfrecs = output_dir + 'test'\n",
"write_tfrecords(test_ds, output_test_tfrecs, num_shards=5)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uEFzV-6ZfBZW"
},
"source": [
"## Configure the DeepLabV3 Mobilenet model for custom dataset"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "_LPEIvLsqSaG"
},
"outputs": [],
"source": [
"train_data_tfrecords = './oxford_iiit_pet_tfrecords/train*'\n",
"val_data_tfrecords = './oxford_iiit_pet_tfrecords/val*'\n",
"test_data_tfrecords = './oxford_iiit_pet_tfrecords/test*'\n",
"trained_model = './trained_model/'\n",
"export_dir = './exported_model/'"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "1ZlSiSRyb1Q6"
},
"source": [
"In Model Garden, the collections of parameters that define a model are called *configs*. Model Garden can create a config based on a known set of parameters via a [factory](https://en.wikipedia.org/wiki/Factory_method_pattern).\n",
"\n",
"\n",
"Use the `mnv2_deeplabv3_pascal` experiment configuration, as defined by `tfm.vision.configs.semantic_segmentation.mnv2_deeplabv3_pascal`.\n",
"\n",
"Please find all the registered experiements [here](https://www.tensorflow.org/api_docs/python/tfm/core/exp_factory/get_exp_config)\n",
"\n",
"The configuration defines an experiment to train a [DeepLabV3](https://arxiv.org/pdf/1706.05587.pdf) model with MobilenetV2 as backbone and [ASPP](https://arxiv.org/pdf/1606.00915v2.pdf) as decoder.\n",
"\n",
"There are also other alternative experiments available such as\n",
"\n",
"* `seg_deeplabv3_pascal`\n",
"* `seg_deeplabv3plus_pascal`\n",
"* `seg_resnetfpn_pascal`\n",
"* `mnv2_deeplabv3plus_cityscapes`\n",
"\n",
"and more. One can switch to them by changing the experiment name argument to the `get_exp_config` function.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "bj5UZ6BkfJCX"
},
"outputs": [],
"source": [
"exp_config = tfm.core.exp_factory.get_exp_config('mnv2_deeplabv3_pascal')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "B8jyG-jGIdFs"
},
"outputs": [],
"source": [
"model_ckpt_path = './model_ckpt/'\n",
"if not os.path.exists(model_ckpt_path):\n",
" os.mkdir(model_ckpt_path)\n",
"\n",
"!gsutil cp gs://tf_model_garden/cloud/vision-2.0/deeplab/deeplabv3_mobilenetv2_coco/best_ckpt-63.data-00000-of-00001 './model_ckpt/'\n",
"!gsutil cp gs://tf_model_garden/cloud/vision-2.0/deeplab/deeplabv3_mobilenetv2_coco/best_ckpt-63.index './model_ckpt/'"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QBYvVFZXhSGQ"
},
"source": [
"### Adjust the model and dataset configurations so that it works with custom dataset."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "o_Z_vWW9-5Sy"
},
"outputs": [],
"source": [
"num_classes = 3\n",
"WIDTH, HEIGHT = 128, 128\n",
"input_size = [HEIGHT, WIDTH, 3]\n",
"BATCH_SIZE = 16\n",
"\n",
"# Backbone Config\n",
"exp_config.task.init_checkpoint = model_ckpt_path + 'best_ckpt-63'\n",
"exp_config.task.freeze_backbone = True\n",
"\n",
"# Model Config\n",
"exp_config.task.model.num_classes = num_classes\n",
"exp_config.task.model.input_size = input_size\n",
"\n",
"# Training Data Config\n",
"exp_config.task.train_data.aug_scale_min = 1.0\n",
"exp_config.task.train_data.aug_scale_max = 1.0\n",
"exp_config.task.train_data.input_path = train_data_tfrecords\n",
"exp_config.task.train_data.global_batch_size = BATCH_SIZE\n",
"exp_config.task.train_data.dtype = 'float32'\n",
"exp_config.task.train_data.output_size = [HEIGHT, WIDTH]\n",
"exp_config.task.train_data.preserve_aspect_ratio = False\n",
"exp_config.task.train_data.seed = 21 # Reproducable Training Data\n",
"\n",
"# Validation Data Config\n",
"exp_config.task.validation_data.input_path = val_data_tfrecords\n",
"exp_config.task.validation_data.global_batch_size = BATCH_SIZE\n",
"exp_config.task.validation_data.dtype = 'float32'\n",
"exp_config.task.validation_data.output_size = [HEIGHT, WIDTH]\n",
"exp_config.task.validation_data.preserve_aspect_ratio = False\n",
"exp_config.task.validation_data.groundtruth_padded_size = [HEIGHT, WIDTH]\n",
"exp_config.task.validation_data.seed = 21 # Reproducable Validation Data"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0HDg5eKniMGJ"
},
"source": [
"### Adjust the trainer configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "WASJZ3gUH8ni"
},
"outputs": [],
"source": [
"logical_device_names = [logical_device.name\n",
" for logical_device in tf.config.list_logical_devices()]\n",
"\n",
"if 'GPU' in ''.join(logical_device_names):\n",
" print('This may be broken in Colab.')\n",
" device = 'GPU'\n",
"elif 'TPU' in ''.join(logical_device_names):\n",
" print('This may be broken in Colab.')\n",
" device = 'TPU'\n",
"else:\n",
" print('Running on CPU is slow, so only train for a few steps.')\n",
" device = 'CPU'\n",
"\n",
"\n",
"train_steps = 2000\n",
"exp_config.trainer.steps_per_loop = int(train_ds.__len__().numpy() // BATCH_SIZE)\n",
"\n",
"exp_config.trainer.summary_interval = exp_config.trainer.steps_per_loop # steps_per_loop = num_of_validation_examples // eval_batch_size\n",
"exp_config.trainer.checkpoint_interval = exp_config.trainer.steps_per_loop\n",
"exp_config.trainer.validation_interval = exp_config.trainer.steps_per_loop\n",
"exp_config.trainer.validation_steps = int(train_ds.__len__().numpy() // BATCH_SIZE) # validation_steps = num_of_validation_examples // eval_batch_size\n",
"exp_config.trainer.train_steps = train_steps\n",
"exp_config.trainer.optimizer_config.warmup.linear.warmup_steps = exp_config.trainer.steps_per_loop\n",
"exp_config.trainer.optimizer_config.learning_rate.type = 'cosine'\n",
"exp_config.trainer.optimizer_config.learning_rate.cosine.decay_steps = train_steps\n",
"exp_config.trainer.optimizer_config.learning_rate.cosine.initial_learning_rate = 0.1\n",
"exp_config.trainer.optimizer_config.warmup.linear.warmup_learning_rate = 0.05"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "R66w5MwkiO8Z"
},
"source": [
"### Print the modified configuration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ckpjzrqfhoSn"
},
"outputs": [],
"source": [
"pp.pprint(exp_config.as_dict())\n",
"display.Javascript('google.colab.output.setIframeHeight(\"500px\");')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "FYwzdGKAiSOV"
},
"source": [
"### Set up the distribution strategy."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "iwiOuYRRqdBi"
},
"outputs": [],
"source": [
"# Setting up the Strategy\n",
"if exp_config.runtime.mixed_precision_dtype == tf.float16:\n",
" tf.keras.mixed_precision.set_global_policy('mixed_float16')\n",
"\n",
"if 'GPU' in ''.join(logical_device_names):\n",
" distribution_strategy = tf.distribute.MirroredStrategy()\n",
"elif 'TPU' in ''.join(logical_device_names):\n",
" tf.tpu.experimental.initialize_tpu_system()\n",
" tpu = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='/device:TPU_SYSTEM:0')\n",
" distribution_strategy = tf.distribute.experimental.TPUStrategy(tpu)\n",
"else:\n",
" print('Warning: this will be really slow.')\n",
" distribution_strategy = tf.distribute.OneDeviceStrategy(logical_device_names[0])\n",
"\n",
"print(\"Done\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZLtk1GIIiVR2"
},
"source": [
"## Create the `Task` object (`tfm.core.base_task.Task`) from the `config_definitions.TaskConfig`.\n",
"\n",
"The `Task` object has all the methods necessary for building the dataset, building the model, and running training \u0026 evaluation. These methods are driven by `tfm.core.train_lib.run_experiment`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ASTB5D2UISSr"
},
"outputs": [],
"source": [
"model_dir = './trained_model/'\n",
"\n",
"with distribution_strategy.scope():\n",
" task = tfm.core.task_factory.get_task(exp_config.task, logging_dir=model_dir)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "YIQ26TW-ihzA"
},
"source": [
"## Visualize a batch of the data."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "412WyIUAIdCr"
},
"outputs": [],
"source": [
"for images, masks in task.build_inputs(exp_config.task.train_data).take(1):\n",
" print()\n",
" print(f'images.shape: {str(images.shape):16} images.dtype: {images.dtype!r}')\n",
" print(f'masks.shape: {str(masks[\"masks\"].shape):16} images.dtype: {masks[\"masks\"].dtype!r}')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3GgluDVJixMd"
},
"source": [
"### Helper function for visualizing the results from TFRecords"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "1kueMMfERvLx"
},
"outputs": [],
"source": [
"def display(display_list):\n",
" plt.figure(figsize=(15, 15))\n",
"\n",
" title = ['Input Image', 'True Mask', 'Predicted Mask']\n",
"\n",
" for i in range(len(display_list)):\n",
" plt.subplot(1, len(display_list), i+1)\n",
" plt.title(title[i])\n",
" plt.imshow(tf.keras.utils.array_to_img(display_list[i]))\n",
"\n",
"\n",
" plt.axis('off')\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZCtt09G7i3dq"
},
"source": [
"### Visualization of training data\n",
"\n",
"Image Title represents what is depicted from the image.\n",
"\n",
"Same helper function can be used while visualizing predicted mask"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YwUPf9V2B6SR"
},
"outputs": [],
"source": [
"num_examples = 3\n",
"\n",
"for images, masks in task.build_inputs(exp_config.task.train_data).take(num_examples):\n",
" display([images[0], masks['masks'][0]])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "MeJ5w8KfjMmP"
},
"source": [
"## Train and evaluate\n",
"**IoU**: is defined as the area of the intersection divided by the area of the union of a predicted mask and ground truth mask."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ru3aHTCySHoH"
},
"outputs": [],
"source": [
"model, eval_logs = tfm.core.train_lib.run_experiment(\n",
" distribution_strategy=distribution_strategy,\n",
" task=task,\n",
" mode='train_and_eval',\n",
" params=exp_config,\n",
" model_dir=model_dir,\n",
" run_post_eval=True)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vt3WmtxhjfGe"
},
"source": [
"## Load logs in tensorboard"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "A9rct_7BoJFb"
},
"outputs": [],
"source": [
"%load_ext tensorboard\n",
"%tensorboard --logdir './trained_model'"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "v6XaGoUuji7P"
},
"source": [
"## Saving and exporting the trained model\n",
"\n",
"The `keras.Model` object returned by `train_lib.run_experiment` expects the data to be normalized by the dataset loader using the same mean and variance statiscics in `preprocess_ops.normalize_image(image, offset=MEAN_RGB, scale=STDDEV_RGB)`. This export function handles those details, so you can pass `tf.uint8` images and get the correct results."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GVsnyqzdnxHd"
},
"outputs": [],
"source": [
"export_saved_model_lib.export_inference_graph(\n",
" input_type='image_tensor',\n",
" batch_size=1,\n",
" input_image_size=[HEIGHT, WIDTH],\n",
" params=exp_config,\n",
" checkpoint_path=tf.train.latest_checkpoint(model_dir),\n",
" export_dir=export_dir)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nM1S-tjIjvAr"
},
"source": [
"## Importing SavedModel"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Nxi9pEwluUcT"
},
"outputs": [],
"source": [
"imported = tf.saved_model.load(export_dir)\n",
"model_fn = imported.signatures['serving_default']"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LbBfl6AUj_My"
},
"source": [
"## Visualize predictions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "qifGt_ohpFhn"
},
"outputs": [],
"source": [
"def create_mask(pred_mask):\n",
" pred_mask = tf.math.argmax(pred_mask, axis=-1)\n",
" pred_mask = pred_mask[..., tf.newaxis]\n",
" return pred_mask[0]\n",
"\n",
"\n",
"for record in test_ds.take(15):\n",
" image = tf.image.resize(record['image'], size=[HEIGHT, WIDTH])\n",
" image = tf.cast(image, dtype=tf.uint8)\n",
" mask = tf.image.resize(record['segmentation_mask'], size=[HEIGHT, WIDTH])\n",
" predicted_mask = model_fn(tf.expand_dims(record['image'], axis=0))\n",
" display([image, mask, create_mask(predicted_mask['logits'])])"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"name": "semantic_segmentation.ipynb",
"provenance": [],
"toc_visible": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|