{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Q2DkyjudkjPu",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f3810600-2bd7-47da-8def-e4d37e0a5a24"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "import os\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "projectPath = '/content/drive/MyDrive/Dissertation_Project'\n",
        "\n",
        "if not os.path.exists(projectPath):\n",
        "    os.makedirs(projectPath)\n",
        "\n",
        "os.chdir(projectPath)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Environmental Setup & Libraries Installation\n",
        "\n",
        "# Install required libraries for geospatial and spatial data processing\n",
        "!pip install rasterio opencv-python-headless scikit-learn imbalanced-learn tensorflow seaborn matplotlib pandas numpy"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nxKGqwIRsxkb",
        "outputId": "0ce52d50-4c88-4d3c-99bf-6f6847f62630"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: rasterio in /usr/local/lib/python3.12/dist-packages (1.5.0)\n",
            "Requirement already satisfied: opencv-python-headless in /usr/local/lib/python3.12/dist-packages (4.13.0.92)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (1.6.1)\n",
            "Requirement already satisfied: imbalanced-learn in /usr/local/lib/python3.12/dist-packages (0.14.1)\n",
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.12/dist-packages (2.20.0)\n",
            "Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (2.0.2)\n",
            "Requirement already satisfied: affine in /usr/local/lib/python3.12/dist-packages (from rasterio) (2.4.0)\n",
            "Requirement already satisfied: attrs in /usr/local/lib/python3.12/dist-packages (from rasterio) (26.1.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from rasterio) (2026.4.22)\n",
            "Requirement already satisfied: click!=8.2.*,>=4.0 in /usr/local/lib/python3.12/dist-packages (from rasterio) (8.3.3)\n",
            "Requirement already satisfied: cligj>=0.5 in /usr/local/lib/python3.12/dist-packages (from rasterio) (0.7.2)\n",
            "Requirement already satisfied: pyparsing in /usr/local/lib/python3.12/dist-packages (from rasterio) (3.3.2)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.16.3)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.5.3)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (3.6.0)\n",
            "Requirement already satisfied: sklearn-compat<0.2,>=0.1.5 in /usr/local/lib/python3.12/dist-packages (from imbalanced-learn) (0.1.5)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=24.3.25 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (25.12.19)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.7.0)\n",
            "Requirement already satisfied: google_pasta>=0.1.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (18.1.1)\n",
            "Requirement already satisfied: opt_einsum>=2.3.2 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from tensorflow) (26.1)\n",
            "Requirement already satisfied: protobuf>=5.28.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (5.29.6)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.32.4)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from tensorflow) (75.2.0)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.17.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: typing_extensions>=3.6.6 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (4.15.0)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.1.2)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.80.0)\n",
            "Requirement already satisfied: tensorboard~=2.20.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.20.0)\n",
            "Requirement already satisfied: keras>=3.10.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.13.2)\n",
            "Requirement already satisfied: h5py>=3.11.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.16.0)\n",
            "Requirement already satisfied: ml_dtypes<1.0.0,>=0.5.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.5.4)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.62.1)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.5.0)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2026.1)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from astunparse>=1.6.0->tensorflow) (0.47.0)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (13.9.4)\n",
            "Requirement already satisfied: namex in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (0.1.0)\n",
            "Requirement already satisfied: optree in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (0.19.0)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.4.7)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.13)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (2.5.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (3.10.2)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (3.1.8)\n",
            "Requirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard~=2.20.0->tensorflow) (3.0.3)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.10.0->tensorflow) (4.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.10.0->tensorflow) (2.20.0)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->keras>=3.10.0->tensorflow) (0.1.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Library Imports\n",
        "\n",
        "import os\n",
        "import cv2\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import rasterio\n",
        "import tensorflow as tf\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "from tensorflow.keras import layers, models\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import confusion_matrix, classification_report, mean_absolute_error, mean_squared_error\n",
        "from imblearn.over_sampling import SMOTE"
      ],
      "metadata": {
        "id": "Bf6H3FB7tLfO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Brain-Inspired Agricultural Image Registration\n",
        "\n",
        "def registerAgriculturalData(referencePath, movingPath, outputPath):\n",
        "    \"\"\"\n",
        "    Brain-inspired registration using ORB features and RANSAC homography.\n",
        "    Variable names converted to camelCase for standardized coding.\n",
        "    \"\"\"\n",
        "    with rasterio.open(referencePath) as refSource:\n",
        "        refImg = refSource.read(1).astype('float32')\n",
        "        refMeta = refSource.meta\n",
        "\n",
        "    with rasterio.open(movingPath) as movSource:\n",
        "        movImg = movSource.read(1).astype('float32')\n",
        "\n",
        "    # Data cleaning\n",
        "    refImgClean = np.nan_to_num(refImg)\n",
        "    movImgClean = np.nan_to_num(movImg)\n",
        "\n",
        "    # Normalization for feature detection\n",
        "    refNorm = cv2.normalize(refImgClean, None, 0, 255, cv2.NORM_MINMAX).astype('uint8')\n",
        "    movNorm = cv2.normalize(movImgClean, None, 0, 255, cv2.NORM_MINMAX).astype('uint8')\n",
        "\n",
        "    # ORB Feature detection\n",
        "    orbDetector = cv2.ORB_create(1000)\n",
        "    keyPoints1, descriptors1 = orbDetector.detectAndCompute(refNorm, None)\n",
        "    keyPoints2, descriptors2 = orbDetector.detectAndCompute(movNorm, None)\n",
        "\n",
        "    if descriptors1 is None or descriptors2 is None:\n",
        "        alignedImg = cv2.resize(movImgClean, (refImg.shape[1], refImg.shape[0]))\n",
        "    else:\n",
        "        bfMatcher = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)\n",
        "        rawMatches = bfMatcher.match(descriptors1, descriptors2)\n",
        "        sortedMatches = sorted(rawMatches, key=lambda x: x.distance)\n",
        "\n",
        "        if len(sortedMatches) > 10:\n",
        "            srcPoints = np.float32([keyPoints2[m.trainIdx].pt for m in sortedMatches]).reshape(-1, 1, 2)\n",
        "            dstPoints = np.float32([keyPoints1[m.queryIdx].pt for m in sortedMatches]).reshape(-1, 1, 2)\n",
        "\n",
        "            homographyMatrix, ransacMask = cv2.findHomography(srcPoints, dstPoints, cv2.RANSAC, 5.0)\n",
        "            alignedImg = cv2.warpPerspective(movImgClean, homographyMatrix, (refImg.shape[1], refImg.shape[0]))\n",
        "        else:\n",
        "            alignedImg = cv2.resize(movImgClean, (refImg.shape[1], refImg.shape[0]))\n",
        "\n",
        "    refMeta.update(dtype='float32', count=1)\n",
        "    with rasterio.open(outputPath, 'w', **refMeta) as outputDest:\n",
        "        outputDest.write(alignedImg.astype('float32'), 1)\n",
        "\n",
        "    print(f\"Registration Complete: {outputPath}\")\n",
        "\n",
        "# Running registration\n",
        "registerAgriculturalData('Calculated_NDVI.tif', 'Rainfall_Data_2018.tif', 'Registered_Rainfall.tif')\n",
        "registerAgriculturalData('Calculated_NDVI.tif', 'Temperature_Data_2018.tif', 'Registered_Temperature.tif')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZAG_GgGGtkfV",
        "outputId": "6f537057-8524-42bc-bb95-eab5c065e5c0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Registration Complete: Registered_Rainfall.tif\n",
            "Registration Complete: Registered_Temperature.tif\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Data Integration, Spatial Patching, and Preprocessing\n",
        "\n",
        "def prepareIntegratedDataset(ndviPath, rainPath, tempPath, csvPath, patchSize=64):\n",
        "    dfSource = pd.read_csv(csvPath)\n",
        "    yieldLabels = dfSource['yieldCategory'].values\n",
        "\n",
        "    with rasterio.open(ndviPath) as s1, rasterio.open(rainPath) as s2, rasterio.open(tempPath) as s3:\n",
        "        ndviData = np.nan_to_num(s1.read(1))\n",
        "        rainData = np.nan_to_num(s2.read(1))\n",
        "        tempData = np.nan_to_num(s3.read(1))\n",
        "\n",
        "    imagePatchList = []\n",
        "    climateStatList = []\n",
        "\n",
        "    for i in range(len(yieldLabels)):\n",
        "        rowIdx = (i * 5) % (ndviData.shape[0] - patchSize)\n",
        "        colIdx = (i * 5) % (ndviData.shape[1] - patchSize)\n",
        "\n",
        "        imagePatchList.append(ndviData[rowIdx:rowIdx+patchSize, colIdx:colIdx+patchSize])\n",
        "\n",
        "        avgRain = np.mean(rainData[rowIdx:rowIdx+patchSize, colIdx:colIdx+patchSize])\n",
        "        avgTemp = np.mean(tempData[rowIdx:rowIdx+patchSize, colIdx:colIdx+patchSize])\n",
        "        climateStatList.append([avgRain, avgTemp])\n",
        "\n",
        "    xImage = np.array(imagePatchList).reshape(-1, patchSize, patchSize, 1)\n",
        "    xClimate = np.array(climateStatList)\n",
        "    yLabel = np.array(yieldLabels)\n",
        "\n",
        "    # Scaling\n",
        "    xImageScaled = (xImage - np.min(xImage)) / (np.max(xImage) - np.min(xImage) + 1e-7)\n",
        "    xClimateScaled = (xClimate - np.min(xClimate, axis=0)) / (np.max(xClimate, axis=0) - np.min(xClimate, axis=0) + 1e-7)\n",
        "\n",
        "    return xImageScaled, xClimateScaled, yLabel\n",
        "\n",
        "\n",
        "xImg, xCli, y = prepareIntegratedDataset('Calculated_NDVI.tif', 'Registered_Rainfall.tif', 'Registered_Temperature.tif', 'Audited_FAOSTAT_Data.csv')"
      ],
      "metadata": {
        "id": "lUYSxMKLuDuN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "311c2a76"
      },
      "source": [
        "xImgTrain, xImgTest, xCliTrain, xCliTest, yTrain, yTest = train_test_split(xImg, xCli, y, test_size=0.2, random_state=42, stratify=y)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "b8352353",
        "outputId": "419dc454-9681-4add-8160-7d5f2fcd8cde"
      },
      "source": [
        "# Apply SMOTE to training data to address class imbalance\n",
        "\n",
        "# Flatten image data for SMOTE\n",
        "xImgTrainFlattened = xImgTrain.reshape(xImgTrain.shape[0], -1)\n",
        "\n",
        "# Combine flattened image data with climate data\n",
        "xCombinedTrain = np.hstack((xImgTrainFlattened, xCliTrain))\n",
        "\n",
        "# Initialize SMOTE\n",
        "sm = SMOTE(random_state=42)\n",
        "\n",
        "# Apply SMOTE to the combined training data\n",
        "xResampledCombined, yResampled = sm.fit_resample(xCombinedTrain, yTrain)\n",
        "\n",
        "# Split resampled data back into image and climate components\n",
        "xImgResampled = xResampledCombined[:, :xImgTrainFlattened.shape[1]]\n",
        "xCliResampled = xResampledCombined[:, xImgTrainFlattened.shape[1]:]\n",
        "\n",
        "# Reshape image data back to its original 4D format\n",
        "xImgResampled = xImgResampled.reshape(-1, xImgTrain.shape[1], xImgTrain.shape[2], xImgTrain.shape[3])\n",
        "\n",
        "print(f\"Original training samples: {len(yTrain)}\")\n",
        "print(f\"Resampled training samples: {len(yResampled)}\")\n",
        "print(f\"Resampled image data shape: {xImgResampled.shape}\")\n",
        "print(f\"Resampled climate data shape: {xCliResampled.shape}\")\n",
        "print(f\"Resampled label distribution: {np.bincount(yResampled)}\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Original training samples: 40\n",
            "Resampled training samples: 42\n",
            "Resampled image data shape: (42, 64, 64, 1)\n",
            "Resampled climate data shape: (42, 2)\n",
            "Resampled label distribution: [14 14 14]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1f455f9a",
        "outputId": "85ca76ab-2080-4145-fcd1-5ccabc09f98a"
      },
      "source": [
        "from tensorflow.keras.applications import VGG16\n",
        "from tensorflow.keras import regularizers\n",
        "\n",
        "def buildHybridModel():\n",
        "    # 1. Spatial Branch: Using VGG16 with partial Fine-Tuning\n",
        "    spatialInput = layers.Input(shape=(64, 64, 1), name='Spatial_Input')\n",
        "    # Repeat channel for VGG compatibility\n",
        "    x = layers.Concatenate()([spatialInput, spatialInput, spatialInput])\n",
        "\n",
        "    baseModel = VGG16(weights='imagenet', include_top=False, input_shape=(64, 64, 3))\n",
        "\n",
        "    # Fine-tuning: Freeze the first 15 layers, unfreeze the rest to learn specific crop patterns\n",
        "    for layer in baseModel.layers[:15]:\n",
        "        layer.trainable = False\n",
        "    for layer in baseModel.layers[15:]:\n",
        "        layer.trainable = True\n",
        "\n",
        "    x = baseModel(x)\n",
        "    x = layers.GlobalAveragePooling2D()(x)\n",
        "    x = layers.Dense(64, activation='relu')(x)\n",
        "    x = layers.Dropout(0.3)(x)\n",
        "\n",
        "    # 2. Temporal Branch: LSTM\n",
        "    temporalInput = layers.Input(shape=(2,), name='Temporal_Input')\n",
        "    y = layers.Reshape((1, 2))(temporalInput)\n",
        "    y = layers.LSTM(32, activation='relu')(y)\n",
        "\n",
        "    # 3. Fusion Layer\n",
        "    merged = layers.concatenate([x, y])\n",
        "    z = layers.Dense(32, activation='relu', kernel_regularizer=regularizers.l2(0.01))(merged)\n",
        "    outputLayer = layers.Dense(3, activation='softmax')(z)\n",
        "\n",
        "    model = models.Model(inputs=[spatialInput, temporalInput], outputs=outputLayer)\n",
        "\n",
        "    # Using a very low learning rate for fine-tuning stability\n",
        "    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n",
        "                  loss='sparse_categorical_crossentropy',\n",
        "                  metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "# Train with Class Weights to force the model to learn 'Medium' class\n",
        "# (Class weights are less critical now after SMOTE, but can still be used if needed)\n",
        "# Recompute class weights for the resampled data\n",
        "classWeights = class_weight.compute_class_weight('balanced', classes=np.unique(yResampled), y=yResampled)\n",
        "classWeightDict = dict(enumerate(classWeights))\n",
        "\n",
        "finalModel = buildHybridModel()\n",
        "history = finalModel.fit(\n",
        "    [xImgResampled, xCliResampled], yResampled,  # Use resampled data\n",
        "    validation_data=([xImgTest, xCliTest], yTest),\n",
        "    epochs=100,\n",
        "    batch_size=2, # Small batch for fine-grained updates\n",
        "    class_weight=classWeightDict, # Critical for 'Medium' class detection\n",
        "    verbose=1\n",
        ")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 664ms/step - accuracy: 0.3095 - loss: 1.6669 - val_accuracy: 0.3000 - val_loss: 1.6015\n",
            "Epoch 2/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 272ms/step - accuracy: 0.3333 - loss: 1.6417 - val_accuracy: 0.3000 - val_loss: 1.5579\n",
            "Epoch 3/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 224ms/step - accuracy: 0.4048 - loss: 1.5387 - val_accuracy: 0.3000 - val_loss: 1.5571\n",
            "Epoch 4/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 198ms/step - accuracy: 0.2381 - loss: 1.5377 - val_accuracy: 0.3000 - val_loss: 1.5371\n",
            "Epoch 5/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 296ms/step - accuracy: 0.4524 - loss: 1.5252 - val_accuracy: 0.3000 - val_loss: 1.5269\n",
            "Epoch 6/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 205ms/step - accuracy: 0.3571 - loss: 1.5404 - val_accuracy: 0.3000 - val_loss: 1.5200\n",
            "Epoch 7/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.2619 - loss: 1.5033 - val_accuracy: 0.3000 - val_loss: 1.5113\n",
            "Epoch 8/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 300ms/step - accuracy: 0.3095 - loss: 1.5180 - val_accuracy: 0.3000 - val_loss: 1.5051\n",
            "Epoch 9/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 199ms/step - accuracy: 0.4048 - loss: 1.4665 - val_accuracy: 0.3000 - val_loss: 1.4936\n",
            "Epoch 10/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 197ms/step - accuracy: 0.3095 - loss: 1.5098 - val_accuracy: 0.4000 - val_loss: 1.4834\n",
            "Epoch 11/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 285ms/step - accuracy: 0.2857 - loss: 1.4894 - val_accuracy: 0.3000 - val_loss: 1.4784\n",
            "Epoch 12/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 229ms/step - accuracy: 0.2143 - loss: 1.5348 - val_accuracy: 0.3000 - val_loss: 1.4714\n",
            "Epoch 13/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 490ms/step - accuracy: 0.3333 - loss: 1.4993 - val_accuracy: 0.3000 - val_loss: 1.4649\n",
            "Epoch 14/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 501ms/step - accuracy: 0.3571 - loss: 1.4822 - val_accuracy: 0.3000 - val_loss: 1.4619\n",
            "Epoch 15/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m16s\u001b[0m 268ms/step - accuracy: 0.3810 - loss: 1.4419 - val_accuracy: 0.3000 - val_loss: 1.4491\n",
            "Epoch 16/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.3095 - loss: 1.4530 - val_accuracy: 0.3000 - val_loss: 1.4419\n",
            "Epoch 17/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 248ms/step - accuracy: 0.2143 - loss: 1.4751 - val_accuracy: 0.4000 - val_loss: 1.4328\n",
            "Epoch 18/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 248ms/step - accuracy: 0.2857 - loss: 1.4460 - val_accuracy: 0.4000 - val_loss: 1.4280\n",
            "Epoch 19/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.2619 - loss: 1.4449 - val_accuracy: 0.4000 - val_loss: 1.4228\n",
            "Epoch 20/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 282ms/step - accuracy: 0.2857 - loss: 1.4304 - val_accuracy: 0.3000 - val_loss: 1.4175\n",
            "Epoch 21/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 216ms/step - accuracy: 0.3095 - loss: 1.4143 - val_accuracy: 0.3000 - val_loss: 1.4147\n",
            "Epoch 22/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 240ms/step - accuracy: 0.3810 - loss: 1.4043 - val_accuracy: 0.3000 - val_loss: 1.4105\n",
            "Epoch 23/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 310ms/step - accuracy: 0.4286 - loss: 1.4127 - val_accuracy: 0.3000 - val_loss: 1.4066\n",
            "Epoch 24/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.3333 - loss: 1.4199 - val_accuracy: 0.3000 - val_loss: 1.4002\n",
            "Epoch 25/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3333 - loss: 1.4049 - val_accuracy: 0.3000 - val_loss: 1.3934\n",
            "Epoch 26/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 288ms/step - accuracy: 0.3571 - loss: 1.3882 - val_accuracy: 0.2000 - val_loss: 1.3891\n",
            "Epoch 27/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.1905 - loss: 1.3908 - val_accuracy: 0.2000 - val_loss: 1.3838\n",
            "Epoch 28/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 199ms/step - accuracy: 0.3333 - loss: 1.3659 - val_accuracy: 0.3000 - val_loss: 1.3791\n",
            "Epoch 29/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 287ms/step - accuracy: 0.3810 - loss: 1.3752 - val_accuracy: 0.3000 - val_loss: 1.3740\n",
            "Epoch 30/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 209ms/step - accuracy: 0.3333 - loss: 1.3741 - val_accuracy: 0.3000 - val_loss: 1.3674\n",
            "Epoch 31/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 395ms/step - accuracy: 0.3571 - loss: 1.3607 - val_accuracy: 0.3000 - val_loss: 1.3626\n",
            "Epoch 32/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 207ms/step - accuracy: 0.2619 - loss: 1.3602 - val_accuracy: 0.3000 - val_loss: 1.3575\n",
            "Epoch 33/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 207ms/step - accuracy: 0.3571 - loss: 1.3514 - val_accuracy: 0.3000 - val_loss: 1.3544\n",
            "Epoch 34/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 275ms/step - accuracy: 0.3333 - loss: 1.3522 - val_accuracy: 0.6000 - val_loss: 1.3493\n",
            "Epoch 35/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.4048 - loss: 1.3306 - val_accuracy: 0.5000 - val_loss: 1.3450\n",
            "Epoch 36/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 206ms/step - accuracy: 0.3333 - loss: 1.3340 - val_accuracy: 0.3000 - val_loss: 1.3416\n",
            "Epoch 37/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 289ms/step - accuracy: 0.2619 - loss: 1.3664 - val_accuracy: 0.5000 - val_loss: 1.3372\n",
            "Epoch 38/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 207ms/step - accuracy: 0.5952 - loss: 1.3065 - val_accuracy: 0.4000 - val_loss: 1.3326\n",
            "Epoch 39/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 258ms/step - accuracy: 0.3095 - loss: 1.3403 - val_accuracy: 0.4000 - val_loss: 1.3290\n",
            "Epoch 40/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.3333 - loss: 1.3238 - val_accuracy: 0.4000 - val_loss: 1.3253\n",
            "Epoch 41/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 262ms/step - accuracy: 0.4048 - loss: 1.3143 - val_accuracy: 0.4000 - val_loss: 1.3206\n",
            "Epoch 42/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 239ms/step - accuracy: 0.3810 - loss: 1.3045 - val_accuracy: 0.4000 - val_loss: 1.3201\n",
            "Epoch 43/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3333 - loss: 1.3085 - val_accuracy: 0.3000 - val_loss: 1.3166\n",
            "Epoch 44/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 249ms/step - accuracy: 0.2619 - loss: 1.3529 - val_accuracy: 0.4000 - val_loss: 1.3122\n",
            "Epoch 45/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 206ms/step - accuracy: 0.2857 - loss: 1.3374 - val_accuracy: 0.3000 - val_loss: 1.3116\n",
            "Epoch 46/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 289ms/step - accuracy: 0.4524 - loss: 1.2931 - val_accuracy: 0.4000 - val_loss: 1.3045\n",
            "Epoch 47/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 196ms/step - accuracy: 0.3571 - loss: 1.3046 - val_accuracy: 0.4000 - val_loss: 1.3012\n",
            "Epoch 48/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 324ms/step - accuracy: 0.3810 - loss: 1.3035 - val_accuracy: 0.5000 - val_loss: 1.2990\n",
            "Epoch 49/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 205ms/step - accuracy: 0.3095 - loss: 1.2965 - val_accuracy: 0.4000 - val_loss: 1.2950\n",
            "Epoch 50/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 207ms/step - accuracy: 0.4762 - loss: 1.2770 - val_accuracy: 0.4000 - val_loss: 1.2924\n",
            "Epoch 51/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 276ms/step - accuracy: 0.1667 - loss: 1.3188 - val_accuracy: 0.4000 - val_loss: 1.2891\n",
            "Epoch 52/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 199ms/step - accuracy: 0.3095 - loss: 1.2912 - val_accuracy: 0.4000 - val_loss: 1.2862\n",
            "Epoch 53/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 256ms/step - accuracy: 0.3333 - loss: 1.2916 - val_accuracy: 0.4000 - val_loss: 1.2835\n",
            "Epoch 54/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.4048 - loss: 1.2625 - val_accuracy: 0.4000 - val_loss: 1.2805\n",
            "Epoch 55/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 330ms/step - accuracy: 0.3333 - loss: 1.2827 - val_accuracy: 0.4000 - val_loss: 1.2784\n",
            "Epoch 56/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.1905 - loss: 1.2892 - val_accuracy: 0.4000 - val_loss: 1.2756\n",
            "Epoch 57/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3810 - loss: 1.2729 - val_accuracy: 0.4000 - val_loss: 1.2734\n",
            "Epoch 58/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 294ms/step - accuracy: 0.3333 - loss: 1.2752 - val_accuracy: 0.4000 - val_loss: 1.2708\n",
            "Epoch 59/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 197ms/step - accuracy: 0.4286 - loss: 1.2649 - val_accuracy: 0.4000 - val_loss: 1.2683\n",
            "Epoch 60/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 299ms/step - accuracy: 0.2857 - loss: 1.2717 - val_accuracy: 0.4000 - val_loss: 1.2660\n",
            "Epoch 61/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 197ms/step - accuracy: 0.2619 - loss: 1.2762 - val_accuracy: 0.4000 - val_loss: 1.2641\n",
            "Epoch 62/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3810 - loss: 1.2646 - val_accuracy: 0.4000 - val_loss: 1.2618\n",
            "Epoch 63/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 298ms/step - accuracy: 0.4286 - loss: 1.2605 - val_accuracy: 0.4000 - val_loss: 1.2597\n",
            "Epoch 64/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 207ms/step - accuracy: 0.4048 - loss: 1.2597 - val_accuracy: 0.4000 - val_loss: 1.2576\n",
            "Epoch 65/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 289ms/step - accuracy: 0.4524 - loss: 1.2586 - val_accuracy: 0.4000 - val_loss: 1.2559\n",
            "Epoch 66/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 198ms/step - accuracy: 0.4524 - loss: 1.2512 - val_accuracy: 0.4000 - val_loss: 1.2536\n",
            "Epoch 67/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 288ms/step - accuracy: 0.2381 - loss: 1.2613 - val_accuracy: 0.3000 - val_loss: 1.2536\n",
            "Epoch 68/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 207ms/step - accuracy: 0.4524 - loss: 1.2474 - val_accuracy: 0.4000 - val_loss: 1.2506\n",
            "Epoch 69/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 208ms/step - accuracy: 0.3571 - loss: 1.2458 - val_accuracy: 0.4000 - val_loss: 1.2481\n",
            "Epoch 70/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 293ms/step - accuracy: 0.4048 - loss: 1.2483 - val_accuracy: 0.4000 - val_loss: 1.2459\n",
            "Epoch 71/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 207ms/step - accuracy: 0.4286 - loss: 1.2382 - val_accuracy: 0.4000 - val_loss: 1.2438\n",
            "Epoch 72/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 292ms/step - accuracy: 0.3571 - loss: 1.2404 - val_accuracy: 0.4000 - val_loss: 1.2419\n",
            "Epoch 73/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 200ms/step - accuracy: 0.4286 - loss: 1.2370 - val_accuracy: 0.4000 - val_loss: 1.2403\n",
            "Epoch 74/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 291ms/step - accuracy: 0.2381 - loss: 1.2391 - val_accuracy: 0.4000 - val_loss: 1.2387\n",
            "Epoch 75/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.4286 - loss: 1.2318 - val_accuracy: 0.4000 - val_loss: 1.2364\n",
            "Epoch 76/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 199ms/step - accuracy: 0.3095 - loss: 1.2459 - val_accuracy: 0.4000 - val_loss: 1.2347\n",
            "Epoch 77/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 298ms/step - accuracy: 0.3571 - loss: 1.2306 - val_accuracy: 0.4000 - val_loss: 1.2333\n",
            "Epoch 78/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 195ms/step - accuracy: 0.3333 - loss: 1.2353 - val_accuracy: 0.4000 - val_loss: 1.2327\n",
            "Epoch 79/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3571 - loss: 1.2318 - val_accuracy: 0.4000 - val_loss: 1.2314\n",
            "Epoch 80/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 291ms/step - accuracy: 0.3095 - loss: 1.2277 - val_accuracy: 0.4000 - val_loss: 1.2301\n",
            "Epoch 81/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 209ms/step - accuracy: 0.3571 - loss: 1.2278 - val_accuracy: 0.1000 - val_loss: 1.2293\n",
            "Epoch 82/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3571 - loss: 1.2247 - val_accuracy: 0.2000 - val_loss: 1.2282\n",
            "Epoch 83/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 291ms/step - accuracy: 0.3810 - loss: 1.2218 - val_accuracy: 0.4000 - val_loss: 1.2254\n",
            "Epoch 84/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.3810 - loss: 1.2162 - val_accuracy: 0.4000 - val_loss: 1.2235\n",
            "Epoch 85/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.3333 - loss: 1.2228 - val_accuracy: 0.4000 - val_loss: 1.2223\n",
            "Epoch 86/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 287ms/step - accuracy: 0.3095 - loss: 1.2203 - val_accuracy: 0.4000 - val_loss: 1.2210\n",
            "Epoch 87/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.3810 - loss: 1.2125 - val_accuracy: 0.4000 - val_loss: 1.2194\n",
            "Epoch 88/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 198ms/step - accuracy: 0.4048 - loss: 1.2141 - val_accuracy: 0.4000 - val_loss: 1.2180\n",
            "Epoch 89/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 287ms/step - accuracy: 0.3095 - loss: 1.2163 - val_accuracy: 0.4000 - val_loss: 1.2167\n",
            "Epoch 90/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 198ms/step - accuracy: 0.4048 - loss: 1.2054 - val_accuracy: 0.4000 - val_loss: 1.2155\n",
            "Epoch 91/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 315ms/step - accuracy: 0.3810 - loss: 1.2154 - val_accuracy: 0.4000 - val_loss: 1.2142\n",
            "Epoch 92/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 198ms/step - accuracy: 0.5476 - loss: 1.1990 - val_accuracy: 0.4000 - val_loss: 1.2130\n",
            "Epoch 93/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 207ms/step - accuracy: 0.3810 - loss: 1.2136 - val_accuracy: 0.4000 - val_loss: 1.2115\n",
            "Epoch 94/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 291ms/step - accuracy: 0.4286 - loss: 1.2052 - val_accuracy: 0.4000 - val_loss: 1.2107\n",
            "Epoch 95/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.3810 - loss: 1.2135 - val_accuracy: 0.4000 - val_loss: 1.2094\n",
            "Epoch 96/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 208ms/step - accuracy: 0.4048 - loss: 1.1985 - val_accuracy: 0.4000 - val_loss: 1.2084\n",
            "Epoch 97/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 381ms/step - accuracy: 0.3810 - loss: 1.2009 - val_accuracy: 0.4000 - val_loss: 1.2073\n",
            "Epoch 98/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 201ms/step - accuracy: 0.2619 - loss: 1.2078 - val_accuracy: 0.4000 - val_loss: 1.2060\n",
            "Epoch 99/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 258ms/step - accuracy: 0.4524 - loss: 1.1960 - val_accuracy: 0.4000 - val_loss: 1.2051\n",
            "Epoch 100/100\n",
            "\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 246ms/step - accuracy: 0.5238 - loss: 1.1889 - val_accuracy: 0.4000 - val_loss: 1.2039\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.applications import VGG16\n",
        "from tensorflow.keras import regularizers\n",
        "\n",
        "def buildHybridModel():\n",
        "    # 1. Spatial Branch: Using VGG16 with partial Fine-Tuning\n",
        "    spatialInput = layers.Input(shape=(64, 64, 1), name='Spatial_Input')\n",
        "    # Repeat channel for VGG compatibility\n",
        "    x = layers.Concatenate()([spatialInput, spatialInput, spatialInput])\n",
        "\n",
        "    baseModel = VGG16(weights='imagenet', include_top=False, input_shape=(64, 64, 3))\n",
        "\n",
        "    # Fine-tuning: Freeze the first 15 layers, unfreeze the rest to learn specific crop patterns\n",
        "    for layer in baseModel.layers[:15]:\n",
        "        layer.trainable = False\n",
        "    for layer in baseModel.layers[15:]:\n",
        "        layer.trainable = True\n",
        "\n",
        "    x = baseModel(x)\n",
        "    x = layers.GlobalAveragePooling2D()(x)\n",
        "    x = layers.Dense(64, activation='relu')(x)\n",
        "    x = layers.Dropout(0.3)(x)\n",
        "\n",
        "    # 2. Temporal Branch: LSTM\n",
        "    temporalInput = layers.Input(shape=(2,), name='Temporal_Input')\n",
        "    y = layers.Reshape((1, 2))(temporalInput)\n",
        "    y = layers.LSTM(32, activation='relu')(y)\n",
        "\n",
        "    # 3. Fusion Layer\n",
        "    merged = layers.concatenate([x, y])\n",
        "    z = layers.Dense(32, activation='relu', kernel_regularizer=regularizers.l2(0.01))(merged)\n",
        "    outputLayer = layers.Dense(3, activation='softmax')(z)\n",
        "\n",
        "    model = models.Model(inputs=[spatialInput, temporalInput], outputs=outputLayer)\n",
        "\n",
        "    # Using a very low learning rate for fine-tuning stability\n",
        "    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),\n",
        "                  loss='sparse_categorical_crossentropy',\n",
        "                  metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "# Train with Class Weights to force the model to learn 'Medium' class\n",
        "from sklearn.utils import class_weight\n",
        "classWeights = class_weight.compute_class_weight('balanced', classes=np.unique(yTrain), y=yTrain)\n",
        "classWeightDict = dict(enumerate(classWeights))\n",
        "\n",
        "finalModel = buildHybridModel()\n",
        "history = finalModel.fit(\n",
        "    [xImgTrain, xCliTrain], yTrain,\n",
        "    validation_data=([xImgTest, xCliTest], yTest),\n",
        "    epochs=100,\n",
        "    batch_size=2, # Small batch for fine-grained updates\n",
        "    class_weight=classWeightDict, # Critical for 'Medium' class detection\n",
        "    verbose=1\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8A5F7XQIugYs",
        "outputId": "909bba21-dc29-4fdd-e1bc-4652167d0024"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 301ms/step - accuracy: 0.2500 - loss: 1.6689 - val_accuracy: 0.3000 - val_loss: 1.5723\n",
            "Epoch 2/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 211ms/step - accuracy: 0.2000 - loss: 1.6297 - val_accuracy: 0.3000 - val_loss: 1.5869\n",
            "Epoch 3/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 275ms/step - accuracy: 0.2750 - loss: 1.5810 - val_accuracy: 0.3000 - val_loss: 1.5586\n",
            "Epoch 4/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 233ms/step - accuracy: 0.4500 - loss: 1.5325 - val_accuracy: 0.3000 - val_loss: 1.5509\n",
            "Epoch 5/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 211ms/step - accuracy: 0.3750 - loss: 1.5210 - val_accuracy: 0.3000 - val_loss: 1.5380\n",
            "Epoch 6/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 301ms/step - accuracy: 0.2000 - loss: 1.5787 - val_accuracy: 0.3000 - val_loss: 1.5316\n",
            "Epoch 7/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 199ms/step - accuracy: 0.4250 - loss: 1.4986 - val_accuracy: 0.3000 - val_loss: 1.5277\n",
            "Epoch 8/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 210ms/step - accuracy: 0.3750 - loss: 1.5198 - val_accuracy: 0.3000 - val_loss: 1.5170\n",
            "Epoch 9/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 275ms/step - accuracy: 0.4500 - loss: 1.4807 - val_accuracy: 0.3000 - val_loss: 1.5064\n",
            "Epoch 10/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 213ms/step - accuracy: 0.3750 - loss: 1.4880 - val_accuracy: 0.3000 - val_loss: 1.4998\n",
            "Epoch 11/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 300ms/step - accuracy: 0.2500 - loss: 1.5385 - val_accuracy: 0.3000 - val_loss: 1.4926\n",
            "Epoch 12/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 212ms/step - accuracy: 0.3500 - loss: 1.4980 - val_accuracy: 0.3000 - val_loss: 1.4816\n",
            "Epoch 13/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 210ms/step - accuracy: 0.3000 - loss: 1.4889 - val_accuracy: 0.3000 - val_loss: 1.4787\n",
            "Epoch 14/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 296ms/step - accuracy: 0.2500 - loss: 1.5102 - val_accuracy: 0.2000 - val_loss: 1.4694\n",
            "Epoch 15/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 213ms/step - accuracy: 0.3250 - loss: 1.4688 - val_accuracy: 0.3000 - val_loss: 1.4640\n",
            "Epoch 16/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 296ms/step - accuracy: 0.3500 - loss: 1.4334 - val_accuracy: 0.3000 - val_loss: 1.4570\n",
            "Epoch 17/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 210ms/step - accuracy: 0.3000 - loss: 1.4646 - val_accuracy: 0.4000 - val_loss: 1.4482\n",
            "Epoch 18/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 298ms/step - accuracy: 0.4000 - loss: 1.4327 - val_accuracy: 0.4000 - val_loss: 1.4427\n",
            "Epoch 19/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 211ms/step - accuracy: 0.2000 - loss: 1.4557 - val_accuracy: 0.4000 - val_loss: 1.4359\n",
            "Epoch 20/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 203ms/step - accuracy: 0.4500 - loss: 1.4215 - val_accuracy: 0.4000 - val_loss: 1.4302\n",
            "Epoch 21/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 311ms/step - accuracy: 0.1750 - loss: 1.4714 - val_accuracy: 0.3000 - val_loss: 1.4265\n",
            "Epoch 22/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 201ms/step - accuracy: 0.3750 - loss: 1.4298 - val_accuracy: 0.0000e+00 - val_loss: 1.4201\n",
            "Epoch 23/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 293ms/step - accuracy: 0.4000 - loss: 1.3984 - val_accuracy: 0.3000 - val_loss: 1.4190\n",
            "Epoch 24/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.2750 - loss: 1.4305 - val_accuracy: 0.3000 - val_loss: 1.4159\n",
            "Epoch 25/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.3750 - loss: 1.4183 - val_accuracy: 0.3000 - val_loss: 1.4081\n",
            "Epoch 26/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 285ms/step - accuracy: 0.3000 - loss: 1.4027 - val_accuracy: 0.3000 - val_loss: 1.4032\n",
            "Epoch 27/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 211ms/step - accuracy: 0.3750 - loss: 1.3919 - val_accuracy: 0.3000 - val_loss: 1.3984\n",
            "Epoch 28/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 210ms/step - accuracy: 0.3750 - loss: 1.3932 - val_accuracy: 0.3000 - val_loss: 1.3948\n",
            "Epoch 29/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 282ms/step - accuracy: 0.3000 - loss: 1.3887 - val_accuracy: 0.3000 - val_loss: 1.3927\n",
            "Epoch 30/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 252ms/step - accuracy: 0.3000 - loss: 1.3782 - val_accuracy: 0.3000 - val_loss: 1.3856\n",
            "Epoch 31/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 264ms/step - accuracy: 0.3000 - loss: 1.3927 - val_accuracy: 0.3000 - val_loss: 1.3819\n",
            "Epoch 32/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.2750 - loss: 1.3773 - val_accuracy: 0.3000 - val_loss: 1.3768\n",
            "Epoch 33/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 265ms/step - accuracy: 0.3500 - loss: 1.3722 - val_accuracy: 0.3000 - val_loss: 1.3732\n",
            "Epoch 34/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 245ms/step - accuracy: 0.3000 - loss: 1.3745 - val_accuracy: 0.3000 - val_loss: 1.3688\n",
            "Epoch 35/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 215ms/step - accuracy: 0.4250 - loss: 1.3599 - val_accuracy: 0.3000 - val_loss: 1.3647\n",
            "Epoch 36/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 278ms/step - accuracy: 0.3500 - loss: 1.3576 - val_accuracy: 0.3000 - val_loss: 1.3599\n",
            "Epoch 37/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 211ms/step - accuracy: 0.2750 - loss: 1.3618 - val_accuracy: 0.3000 - val_loss: 1.3560\n",
            "Epoch 38/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 304ms/step - accuracy: 0.3750 - loss: 1.3561 - val_accuracy: 0.3000 - val_loss: 1.3530\n",
            "Epoch 39/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 200ms/step - accuracy: 0.3250 - loss: 1.3473 - val_accuracy: 0.3000 - val_loss: 1.3494\n",
            "Epoch 40/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 199ms/step - accuracy: 0.2750 - loss: 1.3468 - val_accuracy: 0.3000 - val_loss: 1.3448\n",
            "Epoch 41/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 299ms/step - accuracy: 0.4000 - loss: 1.3385 - val_accuracy: 0.2000 - val_loss: 1.3412\n",
            "Epoch 42/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 202ms/step - accuracy: 0.3500 - loss: 1.3374 - val_accuracy: 0.2000 - val_loss: 1.3384\n",
            "Epoch 43/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 202ms/step - accuracy: 0.2750 - loss: 1.3334 - val_accuracy: 0.2000 - val_loss: 1.3347\n",
            "Epoch 44/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 299ms/step - accuracy: 0.3750 - loss: 1.3288 - val_accuracy: 0.2000 - val_loss: 1.3313\n",
            "Epoch 45/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.3250 - loss: 1.3270 - val_accuracy: 0.2000 - val_loss: 1.3275\n",
            "Epoch 46/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 202ms/step - accuracy: 0.4500 - loss: 1.3195 - val_accuracy: 0.2000 - val_loss: 1.3244\n",
            "Epoch 47/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 302ms/step - accuracy: 0.3500 - loss: 1.3213 - val_accuracy: 0.3000 - val_loss: 1.3203\n",
            "Epoch 48/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 212ms/step - accuracy: 0.2500 - loss: 1.3226 - val_accuracy: 0.2000 - val_loss: 1.3162\n",
            "Epoch 49/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 201ms/step - accuracy: 0.4250 - loss: 1.3113 - val_accuracy: 0.1000 - val_loss: 1.3127\n",
            "Epoch 50/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 297ms/step - accuracy: 0.3000 - loss: 1.3122 - val_accuracy: 0.2000 - val_loss: 1.3112\n",
            "Epoch 51/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 199ms/step - accuracy: 0.3000 - loss: 1.3082 - val_accuracy: 0.1000 - val_loss: 1.3092\n",
            "Epoch 52/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 210ms/step - accuracy: 0.4000 - loss: 1.3079 - val_accuracy: 0.2000 - val_loss: 1.3064\n",
            "Epoch 53/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 298ms/step - accuracy: 0.4000 - loss: 1.3007 - val_accuracy: 0.2000 - val_loss: 1.3028\n",
            "Epoch 54/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 204ms/step - accuracy: 0.3250 - loss: 1.3006 - val_accuracy: 0.2000 - val_loss: 1.2990\n",
            "Epoch 55/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 225ms/step - accuracy: 0.3000 - loss: 1.2996 - val_accuracy: 0.3000 - val_loss: 1.2970\n",
            "Epoch 56/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 262ms/step - accuracy: 0.2750 - loss: 1.2940 - val_accuracy: 0.2000 - val_loss: 1.2940\n",
            "Epoch 57/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 210ms/step - accuracy: 0.3250 - loss: 1.2925 - val_accuracy: 0.2000 - val_loss: 1.2922\n",
            "Epoch 58/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 286ms/step - accuracy: 0.3750 - loss: 1.2893 - val_accuracy: 0.1000 - val_loss: 1.2890\n",
            "Epoch 59/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 227ms/step - accuracy: 0.3250 - loss: 1.2878 - val_accuracy: 0.2000 - val_loss: 1.2875\n",
            "Epoch 60/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 212ms/step - accuracy: 0.4250 - loss: 1.2840 - val_accuracy: 0.2000 - val_loss: 1.2861\n",
            "Epoch 61/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 298ms/step - accuracy: 0.4250 - loss: 1.2812 - val_accuracy: 0.2000 - val_loss: 1.2836\n",
            "Epoch 62/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 203ms/step - accuracy: 0.3750 - loss: 1.2798 - val_accuracy: 0.2000 - val_loss: 1.2813\n",
            "Epoch 63/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 305ms/step - accuracy: 0.4500 - loss: 1.2766 - val_accuracy: 0.2000 - val_loss: 1.2790\n",
            "Epoch 64/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 204ms/step - accuracy: 0.4000 - loss: 1.2738 - val_accuracy: 0.2000 - val_loss: 1.2772\n",
            "Epoch 65/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 327ms/step - accuracy: 0.4500 - loss: 1.2712 - val_accuracy: 0.2000 - val_loss: 1.2746\n",
            "Epoch 66/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 212ms/step - accuracy: 0.4250 - loss: 1.2727 - val_accuracy: 0.2000 - val_loss: 1.2727\n",
            "Epoch 67/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 202ms/step - accuracy: 0.3750 - loss: 1.2684 - val_accuracy: 0.2000 - val_loss: 1.2710\n",
            "Epoch 68/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 303ms/step - accuracy: 0.4000 - loss: 1.2651 - val_accuracy: 0.3000 - val_loss: 1.2686\n",
            "Epoch 69/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 202ms/step - accuracy: 0.3750 - loss: 1.2630 - val_accuracy: 0.2000 - val_loss: 1.2665\n",
            "Epoch 70/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.4000 - loss: 1.2624 - val_accuracy: 0.2000 - val_loss: 1.2646\n",
            "Epoch 71/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 285ms/step - accuracy: 0.3250 - loss: 1.2592 - val_accuracy: 0.2000 - val_loss: 1.2624\n",
            "Epoch 72/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 226ms/step - accuracy: 0.4000 - loss: 1.2562 - val_accuracy: 0.2000 - val_loss: 1.2605\n",
            "Epoch 73/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 202ms/step - accuracy: 0.4000 - loss: 1.2546 - val_accuracy: 0.3000 - val_loss: 1.2586\n",
            "Epoch 74/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 281ms/step - accuracy: 0.4000 - loss: 1.2530 - val_accuracy: 0.2000 - val_loss: 1.2567\n",
            "Epoch 75/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 202ms/step - accuracy: 0.3750 - loss: 1.2507 - val_accuracy: 0.3000 - val_loss: 1.2548\n",
            "Epoch 76/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 283ms/step - accuracy: 0.3500 - loss: 1.2499 - val_accuracy: 0.3000 - val_loss: 1.2528\n",
            "Epoch 77/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 217ms/step - accuracy: 0.3500 - loss: 1.2475 - val_accuracy: 0.3000 - val_loss: 1.2504\n",
            "Epoch 78/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.3750 - loss: 1.2457 - val_accuracy: 0.2000 - val_loss: 1.2484\n",
            "Epoch 79/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 340ms/step - accuracy: 0.3750 - loss: 1.2441 - val_accuracy: 0.2000 - val_loss: 1.2465\n",
            "Epoch 80/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 211ms/step - accuracy: 0.3500 - loss: 1.2418 - val_accuracy: 0.2000 - val_loss: 1.2445\n",
            "Epoch 81/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.4000 - loss: 1.2399 - val_accuracy: 0.2000 - val_loss: 1.2432\n",
            "Epoch 82/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 298ms/step - accuracy: 0.3750 - loss: 1.2383 - val_accuracy: 0.2000 - val_loss: 1.2415\n",
            "Epoch 83/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 225ms/step - accuracy: 0.3750 - loss: 1.2367 - val_accuracy: 0.2000 - val_loss: 1.2400\n",
            "Epoch 84/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 296ms/step - accuracy: 0.3750 - loss: 1.2350 - val_accuracy: 0.2000 - val_loss: 1.2382\n",
            "Epoch 85/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 215ms/step - accuracy: 0.4250 - loss: 1.2330 - val_accuracy: 0.2000 - val_loss: 1.2364\n",
            "Epoch 86/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.4000 - loss: 1.2318 - val_accuracy: 0.2000 - val_loss: 1.2345\n",
            "Epoch 87/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 301ms/step - accuracy: 0.4000 - loss: 1.2297 - val_accuracy: 0.2000 - val_loss: 1.2330\n",
            "Epoch 88/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 211ms/step - accuracy: 0.3750 - loss: 1.2285 - val_accuracy: 0.2000 - val_loss: 1.2314\n",
            "Epoch 89/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 305ms/step - accuracy: 0.3750 - loss: 1.2269 - val_accuracy: 0.2000 - val_loss: 1.2301\n",
            "Epoch 90/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m8s\u001b[0m 213ms/step - accuracy: 0.4000 - loss: 1.2248 - val_accuracy: 0.2000 - val_loss: 1.2286\n",
            "Epoch 91/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 308ms/step - accuracy: 0.3750 - loss: 1.2235 - val_accuracy: 0.2000 - val_loss: 1.2272\n",
            "Epoch 92/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.4000 - loss: 1.2221 - val_accuracy: 0.2000 - val_loss: 1.2257\n",
            "Epoch 93/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 203ms/step - accuracy: 0.4000 - loss: 1.2204 - val_accuracy: 0.2000 - val_loss: 1.2244\n",
            "Epoch 94/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 299ms/step - accuracy: 0.3750 - loss: 1.2190 - val_accuracy: 0.2000 - val_loss: 1.2230\n",
            "Epoch 95/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 206ms/step - accuracy: 0.3750 - loss: 1.2176 - val_accuracy: 0.2000 - val_loss: 1.2216\n",
            "Epoch 96/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 213ms/step - accuracy: 0.3750 - loss: 1.2157 - val_accuracy: 0.2000 - val_loss: 1.2203\n",
            "Epoch 97/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 278ms/step - accuracy: 0.4000 - loss: 1.2144 - val_accuracy: 0.2000 - val_loss: 1.2190\n",
            "Epoch 98/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 205ms/step - accuracy: 0.4250 - loss: 1.2130 - val_accuracy: 0.2000 - val_loss: 1.2177\n",
            "Epoch 99/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 212ms/step - accuracy: 0.4000 - loss: 1.2116 - val_accuracy: 0.2000 - val_loss: 1.2164\n",
            "Epoch 100/100\n",
            "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 264ms/step - accuracy: 0.4000 - loss: 1.2104 - val_accuracy: 0.2000 - val_loss: 1.2153\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Advanced Results Visualization & Statistical Metrics\n",
        "\n",
        "# 1. Performance Predictions\n",
        "predictions = final_model.predict([xImgTest, xCliTest])\n",
        "yPredClasses = np.argmax(predictions, axis=1)\n",
        "\n",
        "# 2. Extract Key Performance Metrics\n",
        "mae = mean_absolute_error(yTest, yPredClasses)\n",
        "rmse = np.sqrt(mean_squared_error(yTest, yPredClasses))\n",
        "\n",
        "print(\"\\n\" + \"=\"*40)\n",
        "print(\"       DISSERTATION PERFORMANCE METRICS\")\n",
        "print(\"=\"*40)\n",
        "print(f\"Mean Absolute Error (MAE): {mae:.4f}\")\n",
        "print(f\"Root Mean Squared Error (RMSE): {rmse:.4f}\")\n",
        "print(\"=\"*40)\n",
        "\n",
        "# 3. Generate Learning Curves (Accuracy & Loss Graphs)\n",
        "plt.figure(figsize=(12, 5))\n",
        "\n",
        "# Plot accuracy curves\n",
        "plt.subplot(1, 2, 1)\n",
        "plt.plot(history.history['accuracy'], label='Train Accuracy', color='forestgreen', linewidth=2)\n",
        "plt.plot(history.history['val_accuracy'], label='Val Accuracy', color='darkorange', linewidth=2)\n",
        "plt.title('Spatio-Temporal Model Training Accuracy', fontsize=12)\n",
        "plt.xlabel('Epochs', fontsize=10)\n",
        "plt.ylabel('Accuracy', fontsize=10)\n",
        "plt.legend()\n",
        "plt.grid(True, linestyle='--', alpha=0.5)\n",
        "\n",
        "# Plot loss curves\n",
        "plt.subplot(1, 2, 2)\n",
        "plt.plot(history.history['loss'], label='Train Loss', color='crimson', linewidth=2)\n",
        "plt.plot(history.history['val_loss'], label='Val Loss', color='purple', linewidth=2)\n",
        "plt.title('Spatio-Temporal Model Loss Curve', fontsize=12)\n",
        "plt.xlabel('Epochs', fontsize=10)\n",
        "plt.ylabel('Loss', fontsize=10)\n",
        "plt.legend()\n",
        "plt.grid(True, linestyle='--', alpha=0.5)\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n",
        "# 4. Generate Confusion Matrix Heatmap\n",
        "cm = confusion_matrix(yTest, yPredClasses)\n",
        "plt.figure(figsize=(7, 5))\n",
        "sns.heatmap(cm, annot=True, fmt='d', cmap='YlGnBu',\n",
        "            xticklabels=['Low', 'Medium', 'High'],\n",
        "            yticklabels=['Low', 'Medium', 'High'])\n",
        "plt.title('Confusion Matrix: Registered Multimodal Fusion', fontsize=12, pad=15)\n",
        "plt.xlabel('Predicted Yield Categories', fontsize=10)\n",
        "plt.ylabel('True Yield Categories', fontsize=10)\n",
        "plt.show()\n",
        "\n",
        "# 5. Output the Final Scientific Classification Report\n",
        "print(\"\\n--- Final Multi-Class Classification Report ---\")\n",
        "print(classification_report(yTest, yPredClasses, target_names=['Low', 'Medium', 'High'], zero_division=0))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "UJp31OrWu2KR",
        "outputId": "7410752f-112b-448e-e770-838880c1e9b5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step\n",
            "\n",
            "========================================\n",
            "       DISSERTATION PERFORMANCE METRICS\n",
            "========================================\n",
            "Mean Absolute Error (MAE): 0.5000\n",
            "Root Mean Squared Error (RMSE): 0.8367\n",
            "========================================\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 700x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "--- Final Multi-Class Classification Report ---\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "         Low       0.80      1.00      0.89         4\n",
            "      Medium       0.50      0.33      0.40         3\n",
            "        High       0.33      0.33      0.33         3\n",
            "\n",
            "    accuracy                           0.60        10\n",
            "   macro avg       0.54      0.56      0.54        10\n",
            "weighted avg       0.57      0.60      0.58        10\n",
            "\n"
          ]
        }
      ]
    }
  ]
}