{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "private_outputs": true, "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "source": [ "# ==========================================================\n", "# 1. IMPORT LIBRARIES\n", "# ==========================================================\n", "import tensorflow as tf\n", "from tensorflow.keras import layers, models\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import os\n", "import zipfile\n", "import seaborn as sns\n", "from sklearn.metrics import confusion_matrix, classification_report\n", "\n", "print(\"TensorFlow Version:\", tf.__version__)\n", "\n", "# ==========================================================\n", "# 2. UPLOAD AND EXTRACT DATASET (COLAB)\n", "# ==========================================================\n", "from google.colab import files\n", "uploaded = files.upload()\n", "\n", "zip_file = None\n", "for file in uploaded.keys():\n", " if file.endswith(\".zip\"):\n", " zip_file = file\n", "\n", "if zip_file is None:\n", " raise ValueError(\"Upload a ZIP dataset.\")\n", "\n", "extract_path = \"/content/intel_dataset2\"\n", "os.makedirs(extract_path, exist_ok=True)\n", "\n", "with zipfile.ZipFile(zip_file, 'r') as zip_ref:\n", " zip_ref.extractall(extract_path)\n", "\n", "print(\"Dataset extracted to:\", extract_path)" ], "metadata": { "id": "FJjdJdPyR7OJ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "\n", "\n", "# ==========================================================\n", "# 3. DATASET PARAMETERS\n", "# ==========================================================\n", "IMG_SIZE = (150,150)\n", "BATCH_SIZE = 32\n", "SEED = 42\n", "\n", "# ==========================================================\n", "# 4. LOAD DATASET\n", "# ==========================================================\n", "extract_path_test = \"/content/intel_dataset2/seg_test/seg_test\"\n", "extract_path_train = \"/content/intel_dataset2/seg_train/seg_train\"\n", "train_ds = tf.keras.preprocessing.image_dataset_from_directory(\n", " extract_path_train,\n", " validation_split=0.2,\n", " subset=\"training\",\n", " seed=SEED,\n", " image_size=IMG_SIZE,\n", " batch_size=BATCH_SIZE\n", ")\n", "\n", "val_ds = tf.keras.preprocessing.image_dataset_from_directory(\n", " extract_path_train,\n", " validation_split=0.2,\n", " subset=\"validation\",\n", " seed=SEED,\n", " image_size=IMG_SIZE,\n", " batch_size=BATCH_SIZE\n", ")\n", "\n", "class_names = train_ds.class_names\n", "num_classes = len(class_names)\n", "\n", "print(\"Classes:\", class_names)\n", "\n", "# ==========================================================\n", "# 5. DATASET OPTIMISATION\n", "# ==========================================================\n", "AUTOTUNE = tf.data.AUTOTUNE\n", "train_ds = train_ds.prefetch(buffer_size=AUTOTUNE)\n", "val_ds = val_ds.prefetch(buffer_size=AUTOTUNE)\n", "\n", "# ==========================================================\n", "# 6. VISUALISE SAMPLE IMAGES\n", "# ==========================================================\n", "plt.figure(figsize=(8,8))\n", "\n", "for images, labels in train_ds.take(1):\n", " for i in range(9):\n", " plt.subplot(3,3,i+1)\n", " plt.imshow(images[i].numpy().astype(\"uint8\"))\n", " plt.title(class_names[labels[i]])\n", " plt.axis(\"off\")\n", "\n", "plt.show()" ], "metadata": { "id": "4FBB1NxJZSjb" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "rYvNuL5t3Hfn", "collapsed": true }, "outputs": [], "source": [ "\n", "\n", "# ==========================================================\n", "# 7. DATA AUGMENTATION\n", "# ==========================================================\n", "data_augmentation = models.Sequential([\n", " layers.RandomFlip(\"horizontal\"),\n", " layers.RandomRotation(0.1),\n", " layers.RandomZoom(0.1)\n", "])\n", "\n", "# ==========================================================\n", "# 8. BUILD CNN MODEL (IMPROVED)\n", "# ==========================================================\n", "model = models.Sequential([\n", "\n", " data_augmentation,\n", " layers.Rescaling(1./255),\n", "\n", " layers.Conv2D(32,3,activation='relu'),\n", " layers.MaxPooling2D(),\n", "\n", " layers.Conv2D(64,3,activation='relu'),\n", " layers.MaxPooling2D(),\n", "\n", " layers.Conv2D(128,3,activation='relu'),\n", " layers.MaxPooling2D(),\n", "\n", " layers.Conv2D(256,3,activation='relu'),\n", " layers.MaxPooling2D(),\n", "\n", " layers.Flatten(),\n", "\n", " layers.Dense(256, activation='relu'),\n", " layers.Dropout(0.5),\n", "\n", " layers.Dense(num_classes, activation='softmax')\n", "])\n", "\n", "model.compile(\n", " optimizer='adam',\n", " loss='sparse_categorical_crossentropy',\n", " metrics=['accuracy']\n", ")\n", "\n", "model.summary()\n", "\n", "# ==========================================================\n", "# 9. EARLY STOPPING\n", "# ==========================================================\n", "early_stop = tf.keras.callbacks.EarlyStopping(\n", " monitor='val_loss',\n", " patience=3,\n", " restore_best_weights=True\n", ")\n", "\n", "# ==========================================================\n", "# 10. TRAIN MODEL\n", "# ==========================================================\n", "history = model.fit(\n", " train_ds,\n", " validation_data=val_ds,\n", " epochs=20,\n", " callbacks=[early_stop]\n", ")\n", "\n", "# ==========================================================\n", "# 11. PLOT TRAINING RESULTS\n", "# ==========================================================\n", "plt.figure(figsize=(8,5))\n", "\n", "plt.plot(history.history['accuracy'], label='Training Accuracy')\n", "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n", "\n", "plt.xlabel(\"Epoch\")\n", "plt.ylabel(\"Accuracy\")\n", "plt.title(\"Training vs Validation Accuracy\")\n", "plt.legend()\n", "plt.show()\n", "\n", "# ==========================================================\n", "# 12. MODEL EVALUATION\n", "# ==========================================================\n", "loss, acc = model.evaluate(val_ds)\n", "\n", "print(\"Validation Accuracy:\", acc)\n", "\n", "# ==========================================================\n", "# 13. CONFUSION MATRIX\n", "# ==========================================================\n", "y_true = []\n", "y_pred = []\n", "\n", "for images, labels in val_ds:\n", " preds = model.predict(images)\n", " y_true.extend(labels.numpy())\n", " y_pred.extend(np.argmax(preds, axis=1))\n", "\n", "cm = confusion_matrix(y_true, y_pred)\n", "\n", "plt.figure(figsize=(8,6))\n", "sns.heatmap(cm, annot=True, fmt=\"d\",\n", " xticklabels=class_names,\n", " yticklabels=class_names,\n", " cmap=\"Blues\")\n", "\n", "plt.xlabel(\"Predicted\")\n", "plt.ylabel(\"Actual\")\n", "plt.title(\"Confusion Matrix\")\n", "plt.show()\n", "\n", "# ==========================================================\n", "# 14. CLASSIFICATION REPORT\n", "# ==========================================================\n", "print(classification_report(y_true, y_pred, target_names=class_names))" ] } ] }