File size: 50,977 Bytes
0372a20 | 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 | {
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"from tensorflow.keras.layers import BatchNormalization, Conv2D, MaxPooling2D\n",
"from tensorflow.keras.preprocessing.image import load_img, img_to_array\n",
"from sklearn.metrics import mean_squared_error\n",
"from tensorflow.keras.initializers import RandomNormal\n",
"from tensorflow.keras.applications.vgg16 import VGG16\n",
"from tensorflow.keras.optimizers import SGD\n",
"from tensorflow.keras.models import Model, Sequential\n",
"from tensorflow.keras import backend as K\n",
"from tensorflow.keras.models import model_from_json\n",
"from matplotlib import cm as CM\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"from tqdm import tqdm\n",
"import scipy.io as io\n",
"from PIL import Image\n",
"import PIL\n",
"import h5py\n",
"import os\n",
"import glob\n",
"import cv2\n",
"import random\n",
"import math\n",
"import sys"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"K.clear_session()\n",
"root = 'DATA'"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"part_A_train = os.path.join(root, 'part_A_final/train_data', 'images')\n",
"part_A_test = os.path.join(root, 'part_A_final/test_data', 'images')\n",
"part_B_train = os.path.join(root, 'part_B_final/train_data', 'images')\n",
"part_B_test = os.path.join(root, 'part_B_final/test_data', 'images')\n",
"temp = 'test_images'\n",
"path_sets = [part_A_train]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total images: 300\n"
]
}
],
"source": [
"img_paths = []\n",
"for path in path_sets:\n",
" for img_path in glob.glob(os.path.join(path, '*.jpg')):\n",
" img_paths.append(str(img_path))\n",
"print(\"Total images:\", len(img_paths))"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def create_img(path):\n",
" \"\"\"Function to load, normalize and return image\"\"\"\n",
" im = Image.open(path).convert('RGB')\n",
" im = np.array(im)\n",
" im = im / 255.0\n",
" \n",
" im[:, :, 0] = (im[:, :, 0] - 0.485) / 0.229\n",
" im[:, :, 1] = (im[:, :, 1] - 0.456) / 0.224\n",
" im[:, :, 2] = (im[:, :, 2] - 0.406) / 0.225\n",
" \n",
" return im\n",
"\n",
"\n",
"def get_input(path):\n",
" path = path[0]\n",
" img = create_img(path)\n",
" return img\n",
"\n",
"\n",
"def get_output(path):\n",
" \"\"\"Import and resize target density map\"\"\"\n",
" gt_file = h5py.File(path, 'r')\n",
" target = np.asarray(gt_file['density'])\n",
" \n",
" img = cv2.resize(target, (int(target.shape[1]/8), int(target.shape[0]/8)), \n",
" interpolation=cv2.INTER_CUBIC) * 64\n",
" img = np.expand_dims(img, axis=2) # Changed from axis=3 to axis=2\n",
" \n",
" return img\n",
"\n",
"\n",
"\n",
"def preprocess_input(image, target):\n",
" \"\"\"Crop image and target (optional data augmentation)\"\"\"\n",
" crop_size = (int(image.shape[0]/2), int(image.shape[1]/2))\n",
" \n",
" if random.randint(0, 9) <= -1:\n",
" dx = int(random.randint(0, 1) * image.shape[0] * 1./2)\n",
" dy = int(random.randint(0, 1) * image.shape[1] * 1./2)\n",
" else:\n",
" dx = int(random.random() * image.shape[0] * 1./2)\n",
" dy = int(random.random() * image.shape[1] * 1./2)\n",
" \n",
" img = image[dx:crop_size[0]+dx, dy:crop_size[1]+dy]\n",
" target_aug = target[dx:crop_size[0]+dx, dy:crop_size[1]+dy]\n",
" \n",
" return (img, target_aug)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"def image_generator(files, batch_size=1):\n",
" \"\"\"Image data generator\"\"\"\n",
" import numpy as np # Add this line\n",
" while True:\n",
" input_path = np.random.choice(a=files, size=1)\n",
" \n",
" inputt = get_input(input_path)\n",
" # Match the path from preprocessing\n",
" output_path = input_path[0].replace('.jpg', '.h5').replace('images', 'ground')\n",
" \n",
" if not os.path.exists(output_path):\n",
" print(f\"File not found: {output_path}\")\n",
" continue\n",
" \n",
" output = get_output(output_path)\n",
" \n",
" batch_x = np.expand_dims(inputt, axis=0)\n",
" batch_y = np.expand_dims(output, axis=0)\n",
" \n",
" yield (batch_x, batch_y)\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"def save_mod(model, str1, str2):\n",
" \"\"\"Save model weights and architecture\"\"\"\n",
" model.save_weights(str1)\n",
" model_json = model.to_json()\n",
" \n",
" with open(str2, \"w\") as json_file:\n",
" json_file.write(model_json)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def init_weights_vgg(model):\n",
" \"\"\"Initialize VGG16 pretrained weights\"\"\"\n",
" # Use built-in VGG16 with ImageNet weights\n",
" vgg = VGG16(weights='imagenet', include_top=False)\n",
" \n",
" vgg_weights = []\n",
" for layer in vgg.layers:\n",
" if 'conv' in layer.name:\n",
" vgg_weights.append(layer.get_weights())\n",
" \n",
" offset = 0\n",
" i = 0\n",
" while i < 10:\n",
" if 'conv' in model.layers[i+offset].name:\n",
" model.layers[i+offset].set_weights(vgg_weights[i])\n",
" i = i + 1\n",
" else:\n",
" offset = offset + 1\n",
" \n",
" return model\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def euclidean_distance_loss(y_true, y_pred):\n",
" \"\"\"Euclidean distance as a measure of loss (Loss function)\"\"\"\n",
" return tf.sqrt(tf.reduce_sum(tf.square(y_pred - y_true), axis=-1))\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"# def CrowdNet():\n",
"# \"\"\"Neural network model: VGG + Conv\"\"\"\n",
"# # Variable Input Size\n",
"# rows = None\n",
"# cols = None\n",
" \n",
"# # Batch Normalisation option\n",
"# batch_norm = 0\n",
"# kernel = (3, 3)\n",
"# init = RandomNormal(stddev=0.01)\n",
"# model = Sequential()\n",
" \n",
"# # Custom VGG\n",
"# if batch_norm:\n",
"# model.add(Conv2D(64, kernel_size=kernel, input_shape=(rows, cols, 3), \n",
"# activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(64, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same'))\n",
"# model.add(BatchNormalization())\n",
"# else:\n",
"# model.add(Conv2D(64, kernel_size=kernel, activation='relu', padding='same',\n",
"# input_shape=(rows, cols, 3), kernel_initializer=init))\n",
"# model.add(Conv2D(64, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(MaxPooling2D(strides=2))\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
"# model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', \n",
"# kernel_initializer=init))\n",
" \n",
"# # Dilated Conv2D layers\n",
"# model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(256, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(128, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(64, (3, 3), activation='relu', dilation_rate=2, \n",
"# kernel_initializer=init, padding='same'))\n",
"# model.add(Conv2D(1, (1, 1), activation='relu', dilation_rate=1, \n",
"# kernel_initializer=init, padding='same'))\n",
" \n",
"# # Fixed: Use learning_rate instead of lr, removed decay\n",
"\n",
"# sgd = SGD(learning_rate=1e-7, momentum=0.95)\n",
"# model.compile(optimizer=sgd, loss='mse', metrics=['mse']) # Use 'mse' instead\n",
" \n",
"# model = init_weights_vgg(model)\n",
"# return model\n",
"\n",
"def CrowdNet():\n",
" \"\"\"Neural network model: VGG + Conv\"\"\"\n",
" rows = None\n",
" cols = None\n",
" batch_norm = 0\n",
" kernel = (3, 3)\n",
" init = RandomNormal(stddev=0.01)\n",
" model = Sequential()\n",
" \n",
" # VGG layers (without batch norm)\n",
" model.add(Conv2D(64, kernel_size=kernel, activation='relu', padding='same',\n",
" input_shape=(rows, cols, 3), kernel_initializer=init))\n",
" model.add(Conv2D(64, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(MaxPooling2D(strides=2))\n",
" model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(Conv2D(128, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(MaxPooling2D(strides=2))\n",
" model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(Conv2D(256, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(MaxPooling2D(strides=2))\n",
" model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" model.add(Conv2D(512, kernel_size=kernel, activation='relu', padding='same', kernel_initializer=init))\n",
" \n",
" # Dilated Conv layers\n",
" model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(512, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(256, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(128, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(64, (3, 3), activation='relu', dilation_rate=2, kernel_initializer=init, padding='same'))\n",
" model.add(Conv2D(1, (1, 1), activation='relu', dilation_rate=1, kernel_initializer=init, padding='same'))\n",
" \n",
" sgd = SGD(learning_rate=1e-7, momentum=0.95)\n",
" model.compile(optimizer=sgd, loss='mse', metrics=['mse'], run_eagerly=True) # Added run_eagerly=True\n",
" \n",
" model = init_weights_vgg(model)\n",
" return model\n",
"\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Building model...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\adity\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\convolutional\\base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
" super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
]
}
],
"source": [
"# Build model\n",
"print(\"Building model...\")\n",
"model = CrowdNet()\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1mModel: \"sequential\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,792</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">36,928</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">147,584</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">590,080</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">590,080</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,180,160</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_11 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_12 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_13 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,179,904</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_14 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, │ <span style=\"color: #00af00; text-decoration-color: #00af00\">295,040</span> │\n",
"│ │ <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">73,792</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_16 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">65</span> │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"</pre>\n"
],
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m1,792\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m73,856\u001b[0m │\n",
"│ │ \u001b[38;5;34m128\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m147,584\u001b[0m │\n",
"│ │ \u001b[38;5;34m128\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │\n",
"│ │ \u001b[38;5;34m128\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m295,168\u001b[0m │\n",
"│ │ \u001b[38;5;34m256\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m590,080\u001b[0m │\n",
"│ │ \u001b[38;5;34m256\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m590,080\u001b[0m │\n",
"│ │ \u001b[38;5;34m256\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │\n",
"│ │ \u001b[38;5;34m256\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m1,180,160\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m2,359,808\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_9 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m2,359,808\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m2,359,808\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_11 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m2,359,808\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_12 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m2,359,808\u001b[0m │\n",
"│ │ \u001b[38;5;34m512\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_13 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m1,179,904\u001b[0m │\n",
"│ │ \u001b[38;5;34m256\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_14 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, │ \u001b[38;5;34m295,040\u001b[0m │\n",
"│ │ \u001b[38;5;34m128\u001b[0m) │ │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_15 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m73,792\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_16 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m65\u001b[0m │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">16,263,489</span> (62.04 MB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m16,263,489\u001b[0m (62.04 MB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">16,263,489</span> (62.04 MB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m16,263,489\u001b[0m (62.04 MB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"train_gen = image_generator(img_paths,1)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Checking: data\\part_A_final/train_data\\ground\\IMG_1.h5\n",
"Exists: True\n"
]
}
],
"source": [
"# Test if density maps exist\n",
"test_path = img_paths[0].replace('.jpg', '.h5').replace('images', 'ground')\n",
"print(f\"Checking: {test_path}\")\n",
"print(f\"Exists: {os.path.exists(test_path)}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Starting training...\n",
"Epoch 1/5\n",
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2057s\u001b[0m 104s/step - loss: 0.0270 - mse: 0.0270\n",
"Epoch 2/5\n",
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1935s\u001b[0m 96s/step - loss: 0.0596 - mse: 0.0596\n",
"Epoch 3/5\n",
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2106s\u001b[0m 103s/step - loss: 0.0830 - mse: 0.0830\n",
"Epoch 4/5\n",
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3105s\u001b[0m 158s/step - loss: 0.0255 - mse: 0.0255\n",
"Epoch 5/5\n",
"\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1841s\u001b[0m 92s/step - loss: 0.0355 - mse: 0.0355\n"
]
},
{
"data": {
"text/plain": [
"<keras.src.callbacks.history.History at 0x1d1e927dfd0>"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"# Train model (Fixed: use fit instead of fit_generator)\n",
"import numpy as np\n",
"print(\"Starting training...\")\n",
"model.fit(train_gen, epochs=5, steps_per_epoch=20, verbose=1)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"os.makedirs('weights', exist_ok=True)\n",
"os.makedirs('models', exist_ok=True)\n",
"save_mod(model, \"weights/model_A.weights.h5\", \"models/Model.json\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|