{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "7neExRi1VObU"
      },
      "outputs": [],
      "source": [
        "!pip install -q kagglehub seaborn"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "kYGncHl5VZlz"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import tensorflow as tf\n",
        "import seaborn as sns\n",
        "import kagglehub\n",
        "\n",
        "from tensorflow.keras import layers, models\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from sklearn.metrics import classification_report, confusion_matrix"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MOFWk16eVc_J",
        "outputId": "c3d5db8d-e606-4252-c389-30bc045331b6"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Using Colab cache for faster access to the 'intel-image-classification' dataset.\n",
            "Dataset Path: /kaggle/input/intel-image-classification\n"
          ]
        }
      ],
      "source": [
        "path = kagglehub.dataset_download(\"puneet6060/intel-image-classification\")\n",
        "print(\"Dataset Path:\", path)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PtR8OYjIVwdy",
        "outputId": "2d99a21c-6680-4462-d1ed-e3d1c8b30afa"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['mountain', 'street', 'buildings', 'sea', 'forest', 'glacier']\n"
          ]
        }
      ],
      "source": [
        "base_dir = os.path.join(path, \"seg_train\", \"seg_train\")\n",
        "\n",
        "print(os.listdir(base_dir))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2yUInvmbV0aM",
        "outputId": "cea8f6b9-5b1d-49f9-a26f-aa35b67693ca"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 11230 images belonging to 6 classes.\n",
            "Found 2804 images belonging to 6 classes.\n"
          ]
        }
      ],
      "source": [
        "img_size = 96\n",
        "batch_size = 32\n",
        "\n",
        "train_datagen = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    validation_split=0.2,\n",
        "    rotation_range=20,\n",
        "    zoom_range=0.2,\n",
        "    horizontal_flip=True\n",
        ")\n",
        "\n",
        "train_data = train_datagen.flow_from_directory(\n",
        "    base_dir,\n",
        "    target_size=(img_size, img_size),\n",
        "    batch_size=batch_size,\n",
        "    class_mode='categorical',\n",
        "    subset='training'\n",
        ")\n",
        "\n",
        "val_data = train_datagen.flow_from_directory(\n",
        "    base_dir,\n",
        "    target_size=(img_size, img_size),\n",
        "    batch_size=batch_size,\n",
        "    class_mode='categorical',\n",
        "    subset='validation',\n",
        "    shuffle=False\n",
        ")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "id": "2ApNa-d_V-E-"
      },
      "outputs": [],
      "source": [
        "base_model = tf.keras.applications.MobileNetV2(\n",
        "    input_shape=(96,96,3),\n",
        "    include_top=False,\n",
        "    weights='imagenet'\n",
        ")\n",
        "\n",
        "base_model.trainable = False\n",
        "\n",
        "model = tf.keras.Sequential([\n",
        "    base_model,\n",
        "    tf.keras.layers.GlobalAveragePooling2D(),\n",
        "    tf.keras.layers.Dense(64, activation='relu'),\n",
        "    tf.keras.layers.Dense(6, activation='softmax')\n",
        "])\n",
        "\n",
        "model.compile(\n",
        "    optimizer='adam',\n",
        "    loss='categorical_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "auwwxwZmfxof"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r_ZpwQyLWASF",
        "outputId": "bf4325e6-19cc-404b-aacd-d03921681ae3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m163s\u001b[0m 446ms/step - accuracy: 0.8304 - loss: 0.4728 - val_accuracy: 0.8663 - val_loss: 0.3820\n",
            "Epoch 2/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m191s\u001b[0m 414ms/step - accuracy: 0.8696 - loss: 0.3572 - val_accuracy: 0.8652 - val_loss: 0.3650\n",
            "Epoch 3/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m146s\u001b[0m 415ms/step - accuracy: 0.8786 - loss: 0.3262 - val_accuracy: 0.8695 - val_loss: 0.3640\n",
            "Epoch 4/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m147s\u001b[0m 419ms/step - accuracy: 0.8849 - loss: 0.3032 - val_accuracy: 0.8734 - val_loss: 0.3448\n",
            "Epoch 5/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 399ms/step - accuracy: 0.8902 - loss: 0.2903 - val_accuracy: 0.8730 - val_loss: 0.3481\n",
            "Epoch 6/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m144s\u001b[0m 409ms/step - accuracy: 0.8966 - loss: 0.2769 - val_accuracy: 0.8759 - val_loss: 0.3496\n",
            "Epoch 7/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 402ms/step - accuracy: 0.8988 - loss: 0.2651 - val_accuracy: 0.8730 - val_loss: 0.3475\n",
            "Epoch 8/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m153s\u001b[0m 437ms/step - accuracy: 0.9047 - loss: 0.2544 - val_accuracy: 0.8752 - val_loss: 0.3477\n",
            "Epoch 9/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 401ms/step - accuracy: 0.9045 - loss: 0.2604 - val_accuracy: 0.8713 - val_loss: 0.3612\n",
            "Epoch 10/10\n",
            "\u001b[1m351/351\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m144s\u001b[0m 411ms/step - accuracy: 0.9045 - loss: 0.2497 - val_accuracy: 0.8723 - val_loss: 0.3547\n"
          ]
        }
      ],
      "source": [
        "history = model.fit(\n",
        "    train_data,\n",
        "    validation_data=val_data,\n",
        "    epochs=10\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "id": "iEM8J8IGX5b9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "outputId": "1cacffb3-9a8e-44ae-b48c-25b7f9557c83"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.figure(figsize=(12,5))\n",
        "\n",
        "\n",
        "plt.subplot(1,2,1)\n",
        "plt.plot(history.history['accuracy'])\n",
        "plt.plot(history.history['val_accuracy'])\n",
        "plt.title('Model Accuracy')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend(['Train','Validation'])\n",
        "\n",
        "\n",
        "plt.subplot(1,2,2)\n",
        "plt.plot(history.history['loss'])\n",
        "plt.plot(history.history['val_loss'])\n",
        "plt.title('Model Loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend(['Train','Validation'])\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "metadata": {
        "id": "YhXYPLkQYAIE",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "350d6061-4f2a-41de-b645-29341c7f6b6e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m88/88\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 417ms/step\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.96      0.83      0.89       438\n",
            "           1       0.98      0.96      0.97       454\n",
            "           2       0.83      0.79      0.81       480\n",
            "           3       0.84      0.82      0.83       502\n",
            "           4       0.83      0.93      0.88       454\n",
            "           5       0.85      0.95      0.90       476\n",
            "\n",
            "    accuracy                           0.88      2804\n",
            "   macro avg       0.88      0.88      0.88      2804\n",
            "weighted avg       0.88      0.88      0.88      2804\n",
            "\n"
          ]
        }
      ],
      "source": [
        "preds = model.predict(val_data)\n",
        "y_pred = np.argmax(preds, axis=1)\n",
        "y_true = val_data.classes\n",
        "\n",
        "print(classification_report(y_true, y_pred))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "metadata": {
        "id": "S885anpaYEqh",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "outputId": "13f38367-e13e-457a-fff5-f128c2c3f62f"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\n",
        "\n",
        "plt.figure(figsize=(8,6))\n",
        "sns.heatmap(cm, annot=True, fmt='d')\n",
        "plt.title('Confusion Matrix')\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Actual')\n",
        "plt.show()"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}