{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "qWty393oiaBu"
   },
   "outputs": [],
   "source": [
    "import sys, cv2, glob, os, time\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import numpy as np \n",
    "import pandas as pd \n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "import os\n",
    "import glob\n",
    "import cv2\n",
    "from sklearn.utils import shuffle\n",
    "\n",
    "import re,string\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from nltk.corpus import stopwords\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from warnings import filterwarnings\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report, roc_auc_score, roc_curve\n",
    "from tensorflow.keras.models import Sequential\n",
    "from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization,MaxPooling2D,Activation,GlobalAveragePooling2D\n",
    "from keras import models, Model\n",
    "from keras import layers\n",
    "import tensorflow as tf\n",
    "import os\n",
    "import os.path\n",
    "from pathlib import Path\n",
    "import cv2\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from sklearn.model_selection import train_test_split\n",
    "from keras import regularizers\n",
    "from keras.optimizers import RMSprop,Adam"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "fz44upqpi2dL"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import classification_report\n",
    "from sklearn.metrics import confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "-36JkmwSi2iS"
   },
   "outputs": [],
   "source": [
    "def get_images(directory):\n",
    "    Images = []\n",
    "    Labels = [] \n",
    "\n",
    "    for labels in os.listdir(directory): \n",
    "\n",
    "        for image_file in os.listdir(directory+labels): \n",
    "            image = cv2.imread(directory+labels+r'/'+image_file) \n",
    "            image = cv2.resize(image,(150,150)) \n",
    "            Images.append(image)\n",
    "            Labels.append(labels)\n",
    "\n",
    "    return shuffle(Images,Labels,random_state=817328462) \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "id": "pgdaDUvU0WLk"
   },
   "outputs": [],
   "source": [
    "# data\n",
    "X_train, y_train = get_images(\"\\Original Images (Primary and Secondary Sources)\\\\10k\\\\\") \n",
    "\n",
    "X_train = np.array(X_train) \n",
    "y_train = np.array(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https"
    },
    "id": "0gF5TePn0WLk",
    "outputId": "9acf0121-050c-4d48-feb3-df36b9cde5ee"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({'Acral Lentiginous Melanoma': 609,\n",
       "         'Alopecia Areata': 542,\n",
       "         'Alopecia Totalis': 502,\n",
       "         'Basal Cell Carcinoma': 335,\n",
       "         'Hemangioma': 328,\n",
       "         'Fordyce Spots': 310,\n",
       "         'Androgenetic Alopecia': 309,\n",
       "         'Granuloma Annulare': 307,\n",
       "         'Herpes Zoster': 297,\n",
       "         'Epidermolytic Hyperkeratosis': 292,\n",
       "         'Arsenicosis': 287,\n",
       "         'Drug Eruptions': 283,\n",
       "         'Dariers Disease': 264,\n",
       "         'Bowens Disease': 241,\n",
       "         'Oral Lichen Planus': 233,\n",
       "         'Impetigo Contagiosa': 227,\n",
       "         'Malignant Melanoma': 226,\n",
       "         'Livedo Reticularis': 222,\n",
       "         'Lichen Planus': 213,\n",
       "         'Discoid Lupus Erythematosus': 213,\n",
       "         'Nevus of Ota': 197,\n",
       "         'Ichthyosis': 181,\n",
       "         'Drug Reactions': 174,\n",
       "         'Lupus Vulgaris': 173,\n",
       "         'Ecthyma': 173,\n",
       "         'Molluscum Contagiosum': 157,\n",
       "         'Hypertrophic Lichen Planus': 156,\n",
       "         'Trichoepithelioma': 142,\n",
       "         'Seborrheic Keratosis': 138,\n",
       "         'Systemic Lupus Erythematosus': 128,\n",
       "         'Mole': 121,\n",
       "         'Pagets Disease': 119,\n",
       "         'Squamous cell carcinoma': 118,\n",
       "         'Pityriasis Rosea': 117,\n",
       "         'Pityriasis Versicolor': 117,\n",
       "         'Vitiligo': 116,\n",
       "         'Linear Scleroderma': 112,\n",
       "         'Keratoderma': 107,\n",
       "         'Nevus Sebaceus': 107,\n",
       "         'Psoriasis': 105,\n",
       "         'Pemphigus Vulgaris': 101,\n",
       "         'Chromoblastomycosis': 101,\n",
       "         'Nevus Spilus': 93,\n",
       "         'Tinea Barbae': 91,\n",
       "         'Pityriasis Lichenoides Chronica': 81,\n",
       "         'Malignant Acanthosis Nigricans': 78,\n",
       "         'Striae Distensae': 67,\n",
       "         'Tinea Corporis': 65,\n",
       "         'Pyogenic Granuloma': 57,\n",
       "         'Tinea Pedis': 53,\n",
       "         'Tuberculosis Verrucosa Cutis': 51,\n",
       "         'Tinea Faciei': 34,\n",
       "         'Melanoacanthoma': 28,\n",
       "         'Nevus': 27,\n",
       "         'Verruca': 27,\n",
       "         'Granulomatous Diseases': 26,\n",
       "         'Solitary Mastocytosis': 22})"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from collections import Counter\n",
    "Counter(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "id": "MivrAWvw0WLl"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10000,)"
      ]
     },
     "execution_count": 6,
      },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.30, random_state = 42,shuffle=True,stratify =y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from imblearn.over_sampling import SMOTE\n",
    "\n",
    "# Reshape Images to 2D\n",
    "n_samples, height, width, n_channels = X_train.shape\n",
    "X_flattened = X_train.reshape(n_samples, -1)\n",
    "\n",
    "# Apply SMOTE\n",
    "sm = SMOTE()\n",
    "X_sm_flattened, y_sm = sm.fit_resample(X_flattened, y_train)\n",
    "\n",
    "# Reshape back to original dimensions\n",
    "X_sm = X_sm_flattened.reshape(-1, height, width, n_channels)\n",
    "\n",
    "print('Resampled dataset shape %s' % Counter(y_sm))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train=X_sm\n",
    "y_train=y_sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "Y3IXgtj3jkcr"
   },
   "outputs": [],
   "source": [
    "n_samples = len(X_train)\n",
    "X_train = X_train.reshape((n_samples, 150,150,3))\n",
    "\n",
    "\n",
    "n_samples = len(X_test)\n",
    "X_test = X_test.reshape((n_samples, 150,150,3))\n",
    "\n",
    "\n",
    "#n_samples = len(X_val)\n",
    "#X_val = X_val.reshape((n_samples,128,128,3))\n",
    "\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "target=y_train.tolist()\n",
    "label_encoder = LabelEncoder()\n",
    "Y = np.array(label_encoder.fit_transform(y_train))\n",
    "y_train = pd.get_dummies(Y).values\n",
    "\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "target=y_test.tolist()\n",
    "label_encoder = LabelEncoder()\n",
    "Y = np.array(label_encoder.fit_transform(y_test))\n",
    "y_test = pd.get_dummies(Y).values\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "oGbJJkwx0WLm"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "3ErIr8ey0WLm",
    "outputId": "a22f3849-d566-4e2f-e37d-1e9acdce7687"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((24282, 150, 150, 3), (24282, 57), (3000, 150, 150, 3), (3000, 57))"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape, y_train.shape, X_test.shape,y_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "Cot_rV3hjkfK"
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense,Flatten,Conv2D,MaxPooling2D,Dropout,BatchNormalization,Activation,MaxPool2D\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, BatchNormalization, Dropout\n",
    "#F1 score\n",
    "import keras.backend as K\n",
    "\n",
    "def f1_score(y_true, y_pred):\n",
    "\n",
    "   \n",
    "    c1 = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n",
    "    c2 = K.sum(K.round(K.clip(y_pred, 0, 1)))\n",
    "    c3 = K.sum(K.round(K.clip(y_true, 0, 1)))\n",
    "\n",
    "    \n",
    "\n",
    "\n",
    "    \n",
    "    precision = c1 / c2\n",
    "\n",
    "   \n",
    "    recall = c1 / c3\n",
    "\n",
    "    \n",
    "    f1_score = 2 * (precision * recall) / (precision + recall)\n",
    "    return f1_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/100\n",
      "380/380 [==============================] - 59s 118ms/step - loss: 2.2467 - accuracy: 0.4321 - val_loss: 0.7366 - val_accuracy: 0.8020\n",
      "Epoch 2/100\n",
      "380/380 [==============================] - 41s 109ms/step - loss: 0.8878 - accuracy: 0.7664 - val_loss: 0.3019 - val_accuracy: 0.9213\n",
      "Epoch 3/100\n",
      "380/380 [==============================] - 42s 109ms/step - loss: 0.5104 - accuracy: 0.8676 - val_loss: 0.2729 - val_accuracy: 0.9293\n",
      "Epoch 4/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.3674 - accuracy: 0.9037 - val_loss: 0.2244 - val_accuracy: 0.9520\n",
      "Epoch 5/100\n",
      "380/380 [==============================] - 41s 108ms/step - loss: 0.2942 - accuracy: 0.9273 - val_loss: 0.1983 - val_accuracy: 0.9563\n",
      "Epoch 6/100\n",
      "380/380 [==============================] - 41s 109ms/step - loss: 0.2271 - accuracy: 0.9441 - val_loss: 0.1508 - val_accuracy: 0.9667\n",
      "Epoch 7/100\n",
      "380/380 [==============================] - 41s 109ms/step - loss: 0.2079 - accuracy: 0.9490 - val_loss: 0.1418 - val_accuracy: 0.9697\n",
      "Epoch 8/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1820 - accuracy: 0.9566 - val_loss: 0.1278 - val_accuracy: 0.9743\n",
      "Epoch 9/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1720 - accuracy: 0.9584 - val_loss: 0.1614 - val_accuracy: 0.9640\n",
      "Epoch 10/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1337 - accuracy: 0.9684 - val_loss: 0.1096 - val_accuracy: 0.9787\n",
      "Epoch 11/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1497 - accuracy: 0.9663 - val_loss: 0.1490 - val_accuracy: 0.9740\n",
      "Epoch 12/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1268 - accuracy: 0.9713 - val_loss: 0.1806 - val_accuracy: 0.9713\n",
      "Epoch 13/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1157 - accuracy: 0.9733 - val_loss: 0.1259 - val_accuracy: 0.9720\n",
      "Epoch 14/100\n",
      "380/380 [==============================] - 42s 112ms/step - loss: 0.1100 - accuracy: 0.9743 - val_loss: 0.1428 - val_accuracy: 0.9710\n",
      "Epoch 15/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.1025 - accuracy: 0.9768 - val_loss: 0.1159 - val_accuracy: 0.9797\n",
      "Epoch 16/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.1190 - accuracy: 0.9725 - val_loss: 0.1093 - val_accuracy: 0.9790\n",
      "Epoch 17/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0862 - accuracy: 0.9801 - val_loss: 0.0940 - val_accuracy: 0.9847\n",
      "Epoch 18/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.1021 - accuracy: 0.9775 - val_loss: 0.0942 - val_accuracy: 0.9827\n",
      "Epoch 19/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0916 - accuracy: 0.9799 - val_loss: 0.0996 - val_accuracy: 0.9823\n",
      "Epoch 20/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0846 - accuracy: 0.9813 - val_loss: 0.1023 - val_accuracy: 0.9810\n",
      "Epoch 21/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0741 - accuracy: 0.9830 - val_loss: 0.1117 - val_accuracy: 0.9807\n",
      "Epoch 22/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0856 - accuracy: 0.9816 - val_loss: 0.2961 - val_accuracy: 0.9687\n",
      "Epoch 23/100\n",
      "380/380 [==============================] - 43s 113ms/step - loss: 0.0799 - accuracy: 0.9827 - val_loss: 0.1541 - val_accuracy: 0.9787\n",
      "Epoch 24/100\n",
      "380/380 [==============================] - 44s 115ms/step - loss: 0.0664 - accuracy: 0.9860 - val_loss: 0.1111 - val_accuracy: 0.9820\n",
      "Epoch 25/100\n",
      "380/380 [==============================] - 44s 115ms/step - loss: 0.0815 - accuracy: 0.9825 - val_loss: 0.1136 - val_accuracy: 0.9830\n",
      "Epoch 26/100\n",
      "380/380 [==============================] - 44s 116ms/step - loss: 0.0761 - accuracy: 0.9844 - val_loss: 0.0977 - val_accuracy: 0.9850\n",
      "Epoch 27/100\n",
      "380/380 [==============================] - 45s 118ms/step - loss: 0.0609 - accuracy: 0.9850 - val_loss: 0.0953 - val_accuracy: 0.9860\n",
      "Epoch 28/100\n",
      "380/380 [==============================] - 46s 122ms/step - loss: 0.0669 - accuracy: 0.9857 - val_loss: 0.1002 - val_accuracy: 0.9843\n",
      "Epoch 29/100\n",
      "380/380 [==============================] - 47s 123ms/step - loss: 0.0570 - accuracy: 0.9874 - val_loss: 0.0851 - val_accuracy: 0.9873\n",
      "Epoch 30/100\n",
      "380/380 [==============================] - 46s 120ms/step - loss: 0.0603 - accuracy: 0.9871 - val_loss: 0.1305 - val_accuracy: 0.9763\n",
      "Epoch 31/100\n",
      "380/380 [==============================] - 44s 116ms/step - loss: 0.0547 - accuracy: 0.9873 - val_loss: 0.1740 - val_accuracy: 0.9770\n",
      "Epoch 32/100\n",
      "380/380 [==============================] - 46s 121ms/step - loss: 0.0762 - accuracy: 0.9844 - val_loss: 0.1393 - val_accuracy: 0.9777\n",
      "Epoch 33/100\n",
      "380/380 [==============================] - 44s 116ms/step - loss: 0.0824 - accuracy: 0.9835 - val_loss: 0.1096 - val_accuracy: 0.9793\n",
      "Epoch 34/100\n",
      "380/380 [==============================] - 44s 116ms/step - loss: 0.0549 - accuracy: 0.9889 - val_loss: 0.1044 - val_accuracy: 0.9867\n",
      "Epoch 35/100\n",
      "380/380 [==============================] - 44s 117ms/step - loss: 0.0520 - accuracy: 0.9880 - val_loss: 0.0969 - val_accuracy: 0.9867\n",
      "Epoch 36/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0509 - accuracy: 0.9887 - val_loss: 0.1124 - val_accuracy: 0.9827\n",
      "Epoch 37/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0539 - accuracy: 0.9876 - val_loss: 0.1182 - val_accuracy: 0.9833\n",
      "Epoch 38/100\n",
      "380/380 [==============================] - 42s 109ms/step - loss: 0.0549 - accuracy: 0.9876 - val_loss: 0.1711 - val_accuracy: 0.9740\n",
      "Epoch 39/100\n",
      "380/380 [==============================] - 42s 109ms/step - loss: 0.0555 - accuracy: 0.9885 - val_loss: 0.1105 - val_accuracy: 0.9853\n",
      "Epoch 40/100\n",
      "380/380 [==============================] - 42s 109ms/step - loss: 0.0447 - accuracy: 0.9905 - val_loss: 0.0803 - val_accuracy: 0.9897\n",
      "Epoch 41/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0486 - accuracy: 0.9895 - val_loss: 0.0875 - val_accuracy: 0.9867\n",
      "Epoch 42/100\n",
      "380/380 [==============================] - 42s 109ms/step - loss: 0.0401 - accuracy: 0.9913 - val_loss: 0.1297 - val_accuracy: 0.9820\n",
      "Epoch 43/100\n",
      "380/380 [==============================] - 43s 112ms/step - loss: 0.0553 - accuracy: 0.9879 - val_loss: 0.1115 - val_accuracy: 0.9820\n",
      "Epoch 44/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0557 - accuracy: 0.9888 - val_loss: 0.1394 - val_accuracy: 0.9803\n",
      "Epoch 45/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0567 - accuracy: 0.9882 - val_loss: 0.1026 - val_accuracy: 0.9850\n",
      "Epoch 46/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0404 - accuracy: 0.9906 - val_loss: 0.0913 - val_accuracy: 0.9843\n",
      "Epoch 47/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0537 - accuracy: 0.9894 - val_loss: 0.0606 - val_accuracy: 0.9887\n",
      "Epoch 48/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0379 - accuracy: 0.9914 - val_loss: 0.0887 - val_accuracy: 0.9857\n",
      "Epoch 49/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0385 - accuracy: 0.9919 - val_loss: 0.0841 - val_accuracy: 0.9873\n",
      "Epoch 50/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0522 - accuracy: 0.9897 - val_loss: 0.1127 - val_accuracy: 0.9860\n",
      "Epoch 51/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0532 - accuracy: 0.9895 - val_loss: 0.1308 - val_accuracy: 0.9807\n",
      "Epoch 52/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0427 - accuracy: 0.9902 - val_loss: 0.1070 - val_accuracy: 0.9857\n",
      "Epoch 53/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0363 - accuracy: 0.9918 - val_loss: 0.1120 - val_accuracy: 0.9847\n",
      "Epoch 54/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0439 - accuracy: 0.9900 - val_loss: 0.1186 - val_accuracy: 0.9837\n",
      "Epoch 55/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0462 - accuracy: 0.9905 - val_loss: 0.1161 - val_accuracy: 0.9847\n",
      "Epoch 56/100\n",
      "380/380 [==============================] - 42s 110ms/step - loss: 0.0546 - accuracy: 0.9891 - val_loss: 0.1512 - val_accuracy: 0.9760\n",
      "Epoch 57/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0434 - accuracy: 0.9908 - val_loss: 0.1045 - val_accuracy: 0.9850\n",
      "Epoch 58/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0345 - accuracy: 0.9931 - val_loss: 0.0845 - val_accuracy: 0.9880\n",
      "Epoch 59/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0279 - accuracy: 0.9937 - val_loss: 0.1111 - val_accuracy: 0.9867\n",
      "Epoch 60/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0527 - accuracy: 0.9903 - val_loss: 0.0834 - val_accuracy: 0.9850\n",
      "Epoch 61/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0385 - accuracy: 0.9916 - val_loss: 0.0981 - val_accuracy: 0.9847\n",
      "Epoch 62/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0331 - accuracy: 0.9927 - val_loss: 0.1282 - val_accuracy: 0.9823\n",
      "Epoch 63/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0376 - accuracy: 0.9925 - val_loss: 0.1443 - val_accuracy: 0.9787\n",
      "Epoch 64/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0319 - accuracy: 0.9922 - val_loss: 0.1158 - val_accuracy: 0.9850\n",
      "Epoch 65/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0386 - accuracy: 0.9919 - val_loss: 0.1483 - val_accuracy: 0.9783\n",
      "Epoch 66/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0406 - accuracy: 0.9909 - val_loss: 0.1057 - val_accuracy: 0.9857\n",
      "Epoch 67/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0331 - accuracy: 0.9924 - val_loss: 0.1074 - val_accuracy: 0.9850\n",
      "Epoch 68/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0385 - accuracy: 0.9928 - val_loss: 0.1309 - val_accuracy: 0.9837\n",
      "Epoch 69/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0390 - accuracy: 0.9923 - val_loss: 0.1058 - val_accuracy: 0.9847\n",
      "Epoch 70/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0477 - accuracy: 0.9906 - val_loss: 0.1165 - val_accuracy: 0.9873\n",
      "Epoch 71/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0361 - accuracy: 0.9921 - val_loss: 0.1622 - val_accuracy: 0.9807\n",
      "Epoch 72/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0336 - accuracy: 0.9935 - val_loss: 0.1043 - val_accuracy: 0.9870\n",
      "Epoch 73/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0362 - accuracy: 0.9925 - val_loss: 0.1049 - val_accuracy: 0.9847\n",
      "Epoch 74/100\n",
      "380/380 [==============================] - 42s 112ms/step - loss: 0.0273 - accuracy: 0.9937 - val_loss: 0.0885 - val_accuracy: 0.9887\n",
      "Epoch 75/100\n",
      "380/380 [==============================] - 42s 112ms/step - loss: 0.0268 - accuracy: 0.9940 - val_loss: 0.1083 - val_accuracy: 0.9883\n",
      "Epoch 76/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0496 - accuracy: 0.9915 - val_loss: 0.0923 - val_accuracy: 0.9880\n",
      "Epoch 77/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0415 - accuracy: 0.9908 - val_loss: 0.1200 - val_accuracy: 0.9833\n",
      "Epoch 78/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0254 - accuracy: 0.9947 - val_loss: 0.1085 - val_accuracy: 0.9853\n",
      "Epoch 79/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0414 - accuracy: 0.9917 - val_loss: 0.0714 - val_accuracy: 0.9890\n",
      "Epoch 80/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0268 - accuracy: 0.9939 - val_loss: 0.1133 - val_accuracy: 0.9840\n",
      "Epoch 81/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0350 - accuracy: 0.9928 - val_loss: 0.1204 - val_accuracy: 0.9863\n",
      "Epoch 82/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0312 - accuracy: 0.9936 - val_loss: 0.1177 - val_accuracy: 0.9873\n",
      "Epoch 83/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0251 - accuracy: 0.9941 - val_loss: 0.0836 - val_accuracy: 0.9897\n",
      "Epoch 84/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0247 - accuracy: 0.9945 - val_loss: 0.1248 - val_accuracy: 0.9840\n",
      "Epoch 85/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0322 - accuracy: 0.9939 - val_loss: 0.1176 - val_accuracy: 0.9850\n",
      "Epoch 86/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0369 - accuracy: 0.9916 - val_loss: 0.1089 - val_accuracy: 0.9847\n",
      "Epoch 87/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0272 - accuracy: 0.9942 - val_loss: 0.1003 - val_accuracy: 0.9873\n",
      "Epoch 88/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0318 - accuracy: 0.9932 - val_loss: 0.1140 - val_accuracy: 0.9847\n",
      "Epoch 89/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0424 - accuracy: 0.9928 - val_loss: 0.1174 - val_accuracy: 0.9850\n",
      "Epoch 90/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0283 - accuracy: 0.9939 - val_loss: 0.1153 - val_accuracy: 0.9873\n",
      "Epoch 91/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0277 - accuracy: 0.9944 - val_loss: 0.0865 - val_accuracy: 0.9870\n",
      "Epoch 92/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0336 - accuracy: 0.9934 - val_loss: 0.1068 - val_accuracy: 0.9833\n",
      "Epoch 93/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0307 - accuracy: 0.9936 - val_loss: 0.0946 - val_accuracy: 0.9843\n",
      "Epoch 94/100\n",
      "380/380 [==============================] - 42s 112ms/step - loss: 0.0366 - accuracy: 0.9932 - val_loss: 0.0774 - val_accuracy: 0.9887\n",
      "Epoch 95/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0228 - accuracy: 0.9956 - val_loss: 0.0993 - val_accuracy: 0.9893\n",
      "Epoch 96/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0209 - accuracy: 0.9954 - val_loss: 0.1037 - val_accuracy: 0.9890\n",
      "Epoch 97/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0314 - accuracy: 0.9936 - val_loss: 0.1263 - val_accuracy: 0.9877\n",
      "Epoch 98/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0412 - accuracy: 0.9929 - val_loss: 0.1184 - val_accuracy: 0.9880\n",
      "Epoch 99/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0239 - accuracy: 0.9948 - val_loss: 0.1003 - val_accuracy: 0.9853\n",
      "Epoch 100/100\n",
      "380/380 [==============================] - 42s 111ms/step - loss: 0.0292 - accuracy: 0.9943 - val_loss: 0.1041 - val_accuracy: 0.9863\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.applications import EfficientNetB2\n",
    "from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, concatenate, Dense, Dropout, GlobalAveragePooling2D, Flatten, Add, Multiply\n",
    "from tensorflow.keras.models import Model\n",
    "import tensorflow.keras.backend as K\n",
    "\n",
    "\n",
    "def inception_module(x, filters):\n",
    "    # 1x1 convolution\n",
    "    path1 = Conv2D(filters[0], (1, 1), activation='relu', padding='same')(x)\n",
    "    # 1x1 followed by 3x3\n",
    "    path2 = Conv2D(filters[1], (1, 1), activation='relu', padding='same')(x)\n",
    "    path2 = Conv2D(filters[2], (3, 3), activation='relu', padding='same')(path2)\n",
    "    # Max pooling followed by 1x1\n",
    "    path3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(x)\n",
    "    path3 = Conv2D(filters[3], (1, 1), activation='relu', padding='same')(path3)\n",
    "    return concatenate([path1, path2, path3])\n",
    "\n",
    "\n",
    "def attention_module(x):\n",
    "    attention = GlobalAveragePooling2D()(x)\n",
    "    attention = Dense(K.int_shape(x)[-1] // 8, activation='relu')(attention)\n",
    "    attention = Dense(K.int_shape(x)[-1], activation='sigmoid')(attention)\n",
    "    return Multiply()([x, attention])\n",
    "\n",
    "\n",
    "input_layer = Input(shape=(150, 150, 3))\n",
    "\n",
    "\n",
    "base_model = EfficientNetB2(weights='imagenet', include_top=False, input_tensor=input_layer)\n",
    "for layer in base_model.layers[:-20]: \n",
    "    layer.trainable = False\n",
    "\n",
    "x = base_model.output\n",
    "\n",
    "\n",
    "x = attention_module(x)\n",
    "\n",
    "\n",
    "x = inception_module(x, [32, 48, 64, 16])\n",
    "\n",
    "\n",
    "x = GlobalAveragePooling2D()(x)\n",
    "\n",
    "\n",
    "x = Dense(64, activation='relu')(x)\n",
    "x = Dropout(0.5)(x)\n",
    "output = Dense(57, activation='softmax')(x)  \n",
    "\n",
    "\n",
    "model4 = Model(inputs=input_layer, outputs=output)\n",
    "\n",
    "\n",
    "model4.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
    "\n",
    "hist4 = model4.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=100, batch_size=64, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "94/94 [==============================] - 8s 49ms/step\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0     1.0000    0.9891    0.9945       183\n",
      "           1     1.0000    0.9816    0.9907       163\n",
      "           2     0.9934    1.0000    0.9967       151\n",
      "           3     1.0000    1.0000    1.0000        93\n",
      "           4     0.9451    1.0000    0.9718        86\n",
      "           5     0.9901    0.9901    0.9901       101\n",
      "           6     0.9730    1.0000    0.9863        72\n",
      "           7     1.0000    1.0000    1.0000        30\n",
      "           8     0.9630    0.9873    0.9750        79\n",
      "           9     0.9836    0.9375    0.9600        64\n",
      "          10     0.9762    0.9647    0.9704        85\n",
      "          11     0.9811    1.0000    0.9905        52\n",
      "          12     0.9811    1.0000    0.9905        52\n",
      "          13     1.0000    0.9886    0.9943        88\n",
      "          14     0.9789    1.0000    0.9894        93\n",
      "          15     1.0000    0.9674    0.9834        92\n",
      "          16     1.0000    1.0000    1.0000         8\n",
      "          17     0.9897    0.9796    0.9846        98\n",
      "          18     0.9889    1.0000    0.9944        89\n",
      "          19     0.9787    0.9787    0.9787        47\n",
      "          20     1.0000    1.0000    1.0000        54\n",
      "          21     0.9848    0.9559    0.9701        68\n",
      "          22     1.0000    1.0000    1.0000        32\n",
      "          23     0.9841    0.9688    0.9764        64\n",
      "          24     1.0000    1.0000    1.0000        34\n",
      "          25     0.9706    0.9851    0.9778        67\n",
      "          26     0.9811    1.0000    0.9905        52\n",
      "          27     1.0000    0.9130    0.9545        23\n",
      "          28     0.9571    0.9853    0.9710        68\n",
      "          29     1.0000    1.0000    1.0000         8\n",
      "          30     1.0000    1.0000    1.0000        36\n",
      "          31     1.0000    0.9574    0.9783        47\n",
      "          32     1.0000    1.0000    1.0000         8\n",
      "          33     0.9412    1.0000    0.9697        32\n",
      "          34     1.0000    1.0000    1.0000        28\n",
      "          35     1.0000    1.0000    1.0000        59\n",
      "          36     1.0000    1.0000    1.0000        70\n",
      "          37     1.0000    1.0000    1.0000        36\n",
      "          38     1.0000    0.9333    0.9655        30\n",
      "          39     0.9231    1.0000    0.9600        24\n",
      "          40     1.0000    1.0000    1.0000        35\n",
      "          41     1.0000    1.0000    1.0000        35\n",
      "          42     1.0000    1.0000    1.0000        32\n",
      "          43     1.0000    0.9412    0.9697        17\n",
      "          44     0.9756    0.9756    0.9756        41\n",
      "          45     1.0000    1.0000    1.0000         7\n",
      "          46     1.0000    0.9714    0.9855        35\n",
      "          47     1.0000    1.0000    1.0000        20\n",
      "          48     0.9000    0.9474    0.9231        38\n",
      "          49     0.9643    1.0000    0.9818        27\n",
      "          50     1.0000    1.0000    1.0000        20\n",
      "          51     1.0000    1.0000    1.0000        10\n",
      "          52     1.0000    0.9375    0.9677        16\n",
      "          53     0.9767    0.9767    0.9767        43\n",
      "          54     1.0000    1.0000    1.0000        15\n",
      "          55     1.0000    1.0000    1.0000         8\n",
      "          56     1.0000    1.0000    1.0000        35\n",
      "\n",
      "    accuracy                         0.9863      3000\n",
      "   macro avg     0.9874    0.9862    0.9866      3000\n",
      "weighted avg     0.9867    0.9863    0.9863      3000\n",
      "\n",
      "[[181   0   1 ...   0   0   0]\n",
      " [  0 160   0 ...   0   0   0]\n",
      " [  0   0 151 ...   0   0   0]\n",
      " ...\n",
      " [  0   0   0 ...  15   0   0]\n",
      " [  0   0   0 ...   0   8   0]\n",
      " [  0   0   0 ...   0   0  35]]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 1200x800 with 0 Axes>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 1200x800 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "predict=model4.predict(X_test)\n",
    "classes=np.argmax(predict,axis=1)\n",
    "rounded_labels=np.argmax(y_test, axis=1)\n",
    "print(classification_report(rounded_labels,classes,digits=4))\n",
    "cnf_matrix=confusion_matrix(rounded_labels,classes)\n",
    "print(cnf_matrix)\n",
    "plt.figure(figsize=(12, 8))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x1200 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "\n",
    "y_true = rounded_labels  \n",
    "y_pred_classes = classes  \n",
    "\n",
    "\n",
    "cm = confusion_matrix(y_true, y_pred_classes)\n",
    "\n",
    "\n",
    "plt.figure(figsize=(15, 12))\n",
    "\n",
    "\n",
    "sns.set(font_scale=0.8)  \n",
    "sns.heatmap(cm, annot=True, fmt='g', cmap='Oranges', cbar=True,\n",
    "            xticklabels=[f'Class {i}' for i in range(1, 58)],  \n",
    "            yticklabels=[f'Class {i}' for i in range(1, 58)],  \n",
    "            linewidths=0.5, linecolor='black')\n",
    "\n",
    "\n",
    "plt.xlabel('Predicted Labels', fontsize=10)\n",
    "plt.ylabel('True Labels', fontsize=10)\n",
    "plt.title('Confusion Matrix (57 Classes)', fontsize=12)\n",
    "\n",
    "\n",
    "plt.xticks(rotation=90, fontsize=8) \n",
    "plt.yticks(rotation=0, fontsize=8) \n",
    "\n",
    "# Display the plot\n",
    "plt.tight_layout()\n",
    "\n",
    "\n",
    "# Show the plot\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy import stats\n",
    "import numpy as np\n",
    "\n",
    "def compute_ci(model, X_test, y_test, model_name):\n",
    "    _, acc = model.evaluate(X_test, y_test, verbose=0)\n",
    "    n = len(X_test)\n",
    "    z = 1.96  # for 95% confidence\n",
    "    se = np.sqrt((acc * (1 - acc)) / n)\n",
    "    ci_lower = acc - z * se\n",
    "    ci_upper = acc + z * se\n",
    "    print(f\"{model_name} Accuracy: {acc:.4f}\")\n",
    "    print(f\"{model_name} 95% CI: ({ci_lower:.4f}, {ci_upper:.4f})\\n\")\n",
    "    return acc\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model 4 Accuracy: 0.9863\n",
      "Model 4 95% CI: (0.9822, 0.9905)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "\n",
    "acc4 = compute_ci(model4, X_test, y_test, \"Model 4\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}