Spaces:
Sleeping
Sleeping
File size: 23,455 Bytes
d00d87c |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "-dt9JrHpxRNH"
},
"source": [
"### Data Preprocessing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting opencv-python\n",
" Downloading opencv-python-4.10.0.84.tar.gz (95.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m95.1/95.1 MB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
"\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
"\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17.0 in /Users/nhradek/Library/jupyterlab-desktop/jlab_server/lib/python3.8/site-packages (from opencv-python) (1.24.2)\n",
"Building wheels for collected packages: opencv-python\n",
" Building wheel for opencv-python (pyproject.toml) ... \u001b[?25l/"
]
}
],
"source": [
"!pip3 install opencv-python"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dHy-E-RQlDoj",
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import cv2\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.manifold import TSNE\n",
"from sklearn.model_selection import train_test_split, cross_val_score, StratifiedKFold\n",
"from sklearn.metrics import accuracy_score, f1_score, confusion_matrix\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from xgboost import XGBClassifier\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.decomposition import PCA\n",
"from scipy.spatial import distance\n",
"from collections import Counter\n",
"import seaborn as sns\n",
"import joblib"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "60Rkg6uR5oyS",
"tags": []
},
"outputs": [],
"source": [
"# Evaluate classifiers\n",
"def evaluate_classifier(y_true, y_pred, classifier_name):\n",
" acc = accuracy_score(y_true, y_pred)\n",
" f1 = f1_score(y_true, y_pred)\n",
" cm = confusion_matrix(y_true, y_pred)\n",
" print(f\"{classifier_name} - Accuracy: {acc:.4f}, F1 Score: {f1:.4f}\")\n",
" print(f\"Confusion Matrix:\\n{cm}\\n\")\n",
"\n",
" plt.figure(figsize=(8, 6))\n",
" sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=['Real Photo', 'CGI'], yticklabels=['Real Photo', 'CGI'])\n",
" plt.title(f'Confusion Matrix for {classifier_name}')\n",
" plt.xlabel('Predicted Labels')\n",
" plt.ylabel('True Labels')\n",
" plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "oIsM1ilT5cQC",
"tags": []
},
"outputs": [],
"source": [
"import numpy as np\n",
"from PIL import Image\n",
"from scipy.fftpack import fft2\n",
"from tensorflow.keras.models import load_model, Model\n",
"\n",
"# Function to apply Fourier transform\n",
"def apply_fourier_transform(image):\n",
" image = np.array(image)\n",
" fft_image = fft2(image)\n",
" return np.abs(fft_image)\n",
"\n",
"# Function to preprocess image\n",
"def preprocess_image(image_path):\n",
" try:\n",
" image = Image.open(image_path).convert('L')\n",
" image = image.resize((256, 256))\n",
" image = apply_fourier_transform(image)\n",
" image = np.expand_dims(image, axis=-1) # Expand dimensions to match model input shape\n",
" image = np.expand_dims(image, axis=0) # Expand to add batch dimension\n",
" return image\n",
" except Exception as e:\n",
" print(f\"Error processing image {image_path}: {e}\")\n",
" return None\n",
"\n",
"# Function to load embedding model and calculate embeddings\n",
"def calculate_embeddings(image_path, model_path='embedding_modelv2.keras'):\n",
" # Load the trained model\n",
" model = load_model(model_path)\n",
"\n",
" # Remove the final classification layer to get embeddings\n",
" embedding_model = Model(inputs=model.input, outputs=model.output)\n",
"\n",
" # Preprocess the image\n",
" preprocessed_image = preprocess_image(image_path)\n",
"\n",
" # Calculate embeddings\n",
" embeddings = embedding_model.predict(preprocessed_image)\n",
"\n",
" return embeddings\n",
"\n",
"\n",
"def calculate_embeddings_folder(folder_path, model_path='embedding_modelv2.keras'):\n",
" embeddings = []\n",
" labels = []\n",
" for filename in os.listdir(folder_path):\n",
" if filename.endswith(\".jpg\") or filename.endswith(\".png\"):\n",
" image_path = os.path.join(folder_path, filename)\n",
" embedding = calculate_embeddings(image_path, model_path)\n",
" embeddings.append(embedding)\n",
" if \"CGI\" in folder_path:\n",
" labels.append(1)\n",
" else:\n",
" labels.append(0)\n",
" return embeddings, labels"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "1lzKxl_gJUEg",
"tags": []
},
"outputs": [],
"source": [
"embeddings = np.load('embeddings.npy')\n",
"labels = np.load('labels.npy')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "12-KegWL3ZZh",
"tags": []
},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(embeddings, labels, test_size=0.2, random_state=42, stratify=labels)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "8YY8_59Lmb1N"
},
"outputs": [],
"source": [
"X_test.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "fSosG_aU3o67"
},
"outputs": [],
"source": [
"xgb_clf = XGBClassifier(use_label_encoder=False, eval_metric='logloss', early_stopping_rounds=10)\n",
"xgb_clf.fit(X_train, y_train, eval_set=[(X_test, y_test)], verbose=False)\n",
"y_pred_xgb = xgb_clf.predict(X_test)\n",
"evaluate_classifier(y_test, y_pred_xgb, \"XGBoost Classifier\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YLhckFv8JYK0"
},
"outputs": [],
"source": [
"from sklearn.neural_network import MLPClassifier as MLP\n",
"from sklearn.svm import SVC"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "MXsnZFDXlNrT"
},
"outputs": [],
"source": [
"# Naive random classifier\n",
"class RandomClassifier:\n",
" def fit(self, X, y):\n",
" pass\n",
"\n",
" def predict(self, X):\n",
" return np.random.choice([0, 1], size=X.shape[0])\n",
"\n",
"class MeanClassifier:\n",
" def fit(self, X, y):\n",
" self.mean_0 = np.mean(X[y == 0], axis=0) if np.any(y == 0) else None\n",
" self.mean_1 = np.mean(X[y == 1], axis=0) if np.any(y == 1) else None\n",
"\n",
" def predict(self, X):\n",
" preds = []\n",
" for x in X:\n",
" dist_0 = distance.euclidean(x, self.mean_0) if self.mean_0 is not None else np.inf\n",
" dist_1 = distance.euclidean(x, self.mean_1) if self.mean_1 is not None else np.inf\n",
" preds.append(1 if dist_1 < dist_0 else 0)\n",
" return np.array(preds)\n",
"\n",
" def predict_proba(self, X):\n",
" # An implementation of probability prediction which uses a softmax function to determine the probability of each class based on the distance to the mean for each prototype\n",
" preds = []\n",
" for x in X:\n",
" dist_0 = distance.euclidean(x, self.mean_0) if self.mean_0 is not None else np\n",
" dist_1 = distance.euclidean(x, self.mean_1) if self.mean_1 is not None else np.inf\n",
" prob_0 = np.exp(-dist_0) / (np.exp(-dist_0) + np.exp(-dist_1))\n",
" prob_1 = np.exp(-dist_1) / (np.exp(-dist_0) + np.exp(-dist_1))\n",
" preds.append([prob_0, prob_1])\n",
" return np.array(preds)\n",
"\n",
" def mean_distance(self, x):\n",
" dist_mean_0 = distance.euclidean(x, self.mean_0) if self.mean_0 is not None else np.inf\n",
" dist_mean_1 = distance.euclidean(x, self.mean_1) if self.mean_1 is not None else np.inf\n",
" return dist_mean_0, dist_mean_1\n",
"\n",
"# Initialize classifiers\n",
"random_clf = RandomClassifier()\n",
"mean_clf = MeanClassifier()\n",
"knn_clf = KNeighborsClassifier(n_neighbors=10)\n",
"rf_clf = RandomForestClassifier(max_depth=10, random_state=42)\n",
"mlp_clf = MLP(hidden_layer_sizes=(128,), max_iter=1000, random_state=42)\n",
"svc_clf = SVC()\n",
"\n",
"# Train classifiers\n",
"random_clf.fit(X_train, y_train)\n",
"mean_clf.fit(X_train, y_train)\n",
"knn_clf.fit(X_train, y_train)\n",
"#xgb_clf.fit(X_train, y_train, eval_set=[(X_test, y_test)], verbose=False)\n",
"rf_clf.fit(X_train, y_train)\n",
"mlp_clf.fit(X_train, y_train)\n",
"svc_clf.fit(X_train, y_train)\n",
"\n",
"# Make predictions\n",
"y_pred_random = random_clf.predict(X_test)\n",
"y_pred_mean = mean_clf.predict(X_test)\n",
"y_pred_knn = knn_clf.predict(X_test)\n",
"#y_pred_xgb = xgb_clf.predict(X_test)\n",
"y_pred_rf = rf_clf.predict(X_test)\n",
"y_pred_mlp = mlp_clf.predict(X_test)\n",
"y_pred_svc = svc_clf.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "sJ52bzdJmDvn"
},
"outputs": [],
"source": [
"evaluate_classifier(y_test, y_pred_random, \"Random Classifier\")\n",
"evaluate_classifier(y_test, y_pred_mean, \"Mean Classifier\")\n",
"evaluate_classifier(y_test, y_pred_knn, \"KNN Classifier\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "DqyF_6STHW7o"
},
"outputs": [],
"source": [
"evaluate_classifier(y_test, y_pred_xgb, \"XGBoost Classifier\")\n",
"evaluate_classifier(y_test, y_pred_rf, \"Random Forest Classifier\")\n",
"evaluate_classifier(y_test, y_pred_svc, \"SVC Classifier\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QfrAONS-DLau"
},
"outputs": [],
"source": [
"evaluate_classifier(y_test, y_pred_mlp, \"MLP Classifier\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "awoV0KS8_3Bi"
},
"outputs": [],
"source": [
"test_filename = \"neytiri.png\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ddV4s5IUAaCc"
},
"outputs": [],
"source": [
"test_embeddings = calculate_embeddings(test_filename, model_path='embedding_modelv2.keras')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9yEk_X2rEH4K"
},
"outputs": [],
"source": [
"def print_prob(model, image_path):\n",
" test_embeddings = calculate_embeddings(image_path, model_path='embedding_modelv2.keras')\n",
" probs = model.predict_proba(test_embeddings)\n",
" print(f\"Real Photo Probability: {probs[0][0]:.4f}\")\n",
" print(f\"CGI Probability: {probs[0][1]:.4f}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "yD2JCKyJROb6"
},
"outputs": [],
"source": [
"print_prob(mlp_clf, test_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "A7Nu_ABnRpT8"
},
"outputs": [],
"source": [
"print_prob(mean_clf, test_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "AFJJuPG6Rpdz"
},
"outputs": [],
"source": [
"print_prob(xgb_clf, test_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Wil3P5JcRYNX"
},
"outputs": [],
"source": [
"print_prob(rf_clf, test_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "14O37IoKZCEW"
},
"outputs": [],
"source": [
"print_prob(knn_clf, test_filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "gi5Vdf-bQElG"
},
"outputs": [],
"source": [
"dist = np.round(mean_clf.mean_distance(test_embeddings[0]), 2)\n",
"print(f\"Dist to real mean {dist[0]}\")\n",
"print(f\"Dist to CGI mean {dist[1]}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3RkM68Li8Kh0"
},
"outputs": [],
"source": [
"def embedding_distance(image_path_1, image_path_2):\n",
" embedding_1 = calculate_embeddings(image_path_1)\n",
" embedding_2 = calculate_embeddings(image_path_2)\n",
" distance = np.linalg.norm(embedding_1 - embedding_2)\n",
" return distance"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "x5GprsHRwkEX"
},
"source": [
"## Visualizing Feature Space"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "oDx-07WfOd-2"
},
"outputs": [],
"source": [
"# prompt: How can I plot embeddings on a t-SNE scatter plot and colored by the label? A label of 1 should be \"CGI\" in the legend and 0 should be \"Real Photo\"\n",
"\n",
"import matplotlib.pyplot as plt\n",
"# Apply t-SNE\n",
"tsne = TSNE(n_components=2, random_state=42)\n",
"embeddings_2d = tsne.fit_transform(embeddings)\n",
"\n",
"# Plot the embeddings\n",
"plt.figure(figsize=(10, 7))\n",
"sns.scatterplot(\n",
" x=embeddings_2d[:, 0],\n",
" y=embeddings_2d[:, 1],\n",
" hue=['CGI' if label == 1 else 'Real Photo' for label in labels], # Map labels to strings\n",
" palette=sns.color_palette(\"hsv\", 2),\n",
" legend=\"full\"\n",
")\n",
"plt.title(\"t-SNE of Image Embeddings\")\n",
"plt.xlabel(\"t-SNE component 1\")\n",
"plt.ylabel(\"t-SNE component 2\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "BKyYu-8won0l"
},
"outputs": [],
"source": [
"# prompt: Can you write a function that visualizes the embeddings using t-sne with the labels but allows a parameter which is an image path and preprocesses the image and calculates the embeddings and plots this embedding as well?\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"def visualize_embeddings_with_new_image(image_path, embeddings, labels):\n",
" \"\"\"\n",
" Visualizes embeddings using t-SNE, including a new image's embedding.\n",
"\n",
" Args:\n",
" image_path: Path to the new image.\n",
" embeddings: Existing embeddings.\n",
" labels: Corresponding labels for existing embeddings.\n",
" \"\"\"\n",
"\n",
" # Calculate embedding for the new image\n",
" new_embedding = calculate_embeddings(image_path, model_path='embedding_modelv2.keras')\n",
"\n",
" # Append new embedding and label to existing data\n",
" all_embeddings = np.concatenate((embeddings, new_embedding), axis=0)\n",
" all_labels = np.concatenate((labels, [2]), axis=0) # Assuming 2 is a new label for the new image\n",
"\n",
" # Apply t-SNE\n",
" tsne = TSNE(n_components=2, random_state=42)\n",
" embeddings_2d = tsne.fit_transform(all_embeddings)\n",
"\n",
" # Plot the embeddings\n",
" plt.figure(figsize=(10, 7))\n",
" sns.scatterplot(\n",
" x=embeddings_2d[:-1, 0], # Plot existing embeddings\n",
" y=embeddings_2d[:-1, 1],\n",
" hue=['CGI' if label == 1 else 'Real Photo' for label in all_labels[:-1]],\n",
" palette=sns.color_palette(\"hsv\", 2),\n",
" legend=\"full\"\n",
" )\n",
"\n",
" # Plot the new image's embedding\n",
" plt.scatter(\n",
" x=embeddings_2d[-1, 0],\n",
" y=embeddings_2d[-1, 1],\n",
" color='black',\n",
" marker='*',\n",
" s=200,\n",
" label='New Image'\n",
" )\n",
"\n",
" plt.title(\"t-SNE of Image Embeddings with New Image\")\n",
" plt.xlabel(\"t-SNE component 1\")\n",
" plt.ylabel(\"t-SNE component 2\")\n",
" plt.legend()\n",
" plt.show()\n",
"\n",
"# Example usage:\n",
"# visualize_embeddings_with_new_image(\"path/to/your/new/image.jpg\", embeddings, labels)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "v6jrK3Auo-eM"
},
"outputs": [],
"source": [
"visualize_embeddings_with_new_image(\"neytiri.png\", embeddings, labels)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "JokVT8QNCOCm"
},
"source": [
"### Testing Validation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "QzkDffzBDGce"
},
"outputs": [],
"source": [
"!unzip Validation.zip"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "UkuPOZXKCNd5"
},
"outputs": [],
"source": [
"cgi_val_images, cgi_val_labels = calculate_embeddings_folder('Validation/CGI')\n",
"photo_val_images, photo_val_labels = calculate_embeddings_folder('Validation/Photo')\n",
"\n",
"print(f\"CGI shape {np.array(cgi_val_images).shape}\")\n",
"print(f\"Photo shape {np.array(photo_val_images).shape}\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "pUE8siFEDF0h"
},
"outputs": [],
"source": [
"# prompt: Can you test the validation images and labels against the XGB, Mean, and KNN classifiers?\n",
"\n",
"import numpy as np\n",
"# Combine validation data\n",
"X_val = np.concatenate((cgi_val_images, photo_val_images), axis=0)\n",
"y_val = np.concatenate((cgi_val_labels, photo_val_labels), axis=0)\n",
"\n",
"# Reshape validation data to match model input\n",
"X_val = X_val.reshape(X_val.shape[0], -1)\n",
"\n",
"# Predict using classifiers\n",
"y_pred_xgb_val = xgb_clf.predict(X_val)\n",
"y_pred_mean_val = mean_clf.predict(X_val)\n",
"y_pred_knn_val = knn_clf.predict(X_val)\n",
"y_pred_svc_val = svc_clf.predict(X_val)\n",
"y_pred_rf_val = rf_clf.predict(X_val)\n",
"y_pred_mlp_val = mlp_clf.predict(X_val)\n",
"\n",
"# Evaluate classifiers on validation set\n",
"evaluate_classifier(y_val, y_pred_xgb_val, \"XGBoost Classifier (Validation)\")\n",
"evaluate_classifier(y_val, y_pred_mean_val, \"Mean Classifier (Validation)\")\n",
"evaluate_classifier(y_val, y_pred_knn_val, \"KNN Classifier (Validation)\")\n",
"evaluate_classifier(y_val, y_pred_svc_val, \"SVC Classifier (Validation)\")\n",
"evaluate_classifier(y_val, y_pred_rf_val, \"Random Forest Classifier (Validation)\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "KFvqq8di5QnS"
},
"source": [
"### Old Preprocessing"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "5-M_iFWC5SOk"
},
"outputs": [],
"source": [
"# Function to load and preprocess images\n",
"def load_images(folder, label):\n",
" images = []\n",
" labels = []\n",
" for filename in os.listdir(folder):\n",
" if filename.endswith(\".jpg\") or filename.endswith(\".png\") or filename.endswith(\".jpeg\"):\n",
" img = cv2.imread(os.path.join(folder, filename), cv2.IMREAD_GRAYSCALE)\n",
" if img is not None:\n",
" img = cv2.resize(img, (256, 256))\n",
" images.append(img)\n",
" labels.append(label)\n",
" return images, labels\n",
"\n",
"pca = PCA(n_components=128)\n",
"# Function to perform Fourier transform and extract features\n",
"def extract_features(images):\n",
" features = []\n",
" for img in images:\n",
" f_transform = np.fft.fft2(img)\n",
" f_shift = np.fft.fftshift(f_transform)\n",
" magnitude_spectrum = 20 * np.log(np.abs(f_shift))\n",
" features.append(magnitude_spectrum.flatten())\n",
" features = pca.fit_transform(features)\n",
" return np.array(features)\n",
"\n",
"# Load and preprocess images from both folders\n",
"cgi_images, cgi_labels = load_images('CGI', 1) # 1 for CGI\n",
"photo_images, photo_labels = load_images('Photo', 0) # 0 for Real Photo\n",
"\n",
"min_length = min(len(cgi_images), len(photo_images))\n",
"cgi_images = cgi_images[:min_length]\n",
"cgi_labels = cgi_labels[:min_length]\n",
"photo_images = photo_images[:min_length]\n",
"photo_labels = photo_labels[:min_length]\n",
"\n",
"# Combine datasets\n",
"images = cgi_images + photo_images\n",
"labels = cgi_labels + photo_labels\n",
"\n",
"print(f\"Number of CGI images: {len(cgi_images)}\")\n",
"print(f\"Number of Photo images: {len(photo_images)}\")\n",
"\n",
"# Extract features\n",
"features = extract_features(images)\n",
"\n",
"# Encode labels\n",
"labels = np.array(labels)\n",
"\n",
"# Split data into training and testing sets\n",
"X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.2, random_state=42, stratify=labels)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "yAqmOxpp-iin"
},
"outputs": [],
"source": [
"X_train.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Dm1lretJBbKs"
},
"outputs": [],
"source": [
"embeddings.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "TlumN_GMBg_F"
},
"outputs": [],
"source": [
"X_test.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "8Fq0dUzHtHeQ"
},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"machine_shape": "hm",
"private_outputs": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.8.16"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|