diff --git a/CNN Image Classification Report.pdf b/CNN Image Classification Report.pdf
new file mode 100644
index 00000000..99033035
Binary files /dev/null and b/CNN Image Classification Report.pdf differ
diff --git a/Project I_Deep Learning_Classification with CNN_Presentation.pdf b/Project I_Deep Learning_Classification with CNN_Presentation.pdf
new file mode 100644
index 00000000..482dc20c
Binary files /dev/null and b/Project I_Deep Learning_Classification with CNN_Presentation.pdf differ
diff --git a/best_model.h5 b/best_model.h5
new file mode 100644
index 00000000..06384db1
Binary files /dev/null and b/best_model.h5 differ
diff --git a/main.ipynb b/main.ipynb
new file mode 100644
index 00000000..dcb267b7
--- /dev/null
+++ b/main.ipynb
@@ -0,0 +1,1161 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from matplotlib import pyplot as plt\n",
+    "from matplotlib import image\n",
+    "from tensorflow.keras.datasets import cifar10\n",
+    "from skimage import color, data, exposure, filters, io, morphology"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(x_train, y_train), (x_test, y_test) = cifar10.load_data()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Display the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training data shape: (50000, 32, 32, 3)\n",
+      "Training labels shape: (50000, 1)\n",
+      "Test data shape: (10000, 32, 32, 3)\n",
+      "Test labels shape: (10000, 1)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Display information about the dataset\n",
+    "print(f'Training data shape: {x_train.shape}')\n",
+    "print(f'Training labels shape: {y_train.shape}')\n",
+    "print(f'Test data shape: {x_test.shape}')\n",
+    "print(f'Test labels shape: {y_test.shape}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Normalization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert to float32 type and normalize (dividing by 255)\n",
+    "x_train = x_train.astype('float32') / 255.0\n",
+    "x_test = x_test.astype('float32') / 255.0"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Data Augmentation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "\n",
+    "# Creating a data generator for data augmentation\n",
+    "datagen = ImageDataGenerator(\n",
+    "    rotation_range=15,       # Random rotation up to 15 degrees\n",
+    "    width_shift_range=0.1,   # Horizontal displacement up to 10%\n",
+    "    height_shift_range=0.1,  # Vertical displacement up to 10%\n",
+    "    horizontal_flip=True     # Horizontal turning\n",
+    ")\n",
+    "\n",
+    "# Adjusting the generator to the training data\n",
+    "datagen.fit(x_train)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## View part of the data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxkAAAMpCAYAAABomf5SAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAADTgUlEQVR4nOz9eZRl51nffV97n/lUnZqrurq6q0ep25ItyZZt2ZaNJxlsbAcbCDi85DUOTtYKvAEcEiAhYCArIwsC5GGFh5UYO85AyPMkYDCWwQFjPA+yZqkltdRzdXV3zXXmffbe7x9yNRLn/K7qbm9bXfL3s5bWsuuqPd/3vfd9qs9vB2mapgYAAAAAGQmf6x0AAAAA8PzCJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBM5a/kl5IksYWFBavVahYEwTd6nwAMkKapbW5u2tzcnIXhzvt8gHEEeO7t5HGEMQS4PlzpOHJFk4yFhQWbn5/PbOcAXLszZ87Y3r17n+vduGqMI8D1YyeOI4whwPVlu3HkiiYZtVrNzMxeescrLJ/vX2R9fVUuWwoTWRsv6peN7x2vytrUhK6ZmU2ODslaMSzIWq5U0SvN5WRpdW1d1qKePsax0VFZC+NI1jrdjqy127pWrpRkzcwstljWWq2GrI2M1vRKU73OblcfY85pmjnnWgwPDcvaUFW3m3yhLGtmZu1OV9bSwPk0MNTH0e3qdfbS/k/p2p2u/fy//2+X++NOs7Xf//YD/93KA67FwuP3yWWXTj0ma3Gsz/HM3iOytvfgUVkzMxvbpQfOckVv8/ijX5S10089JGu9uu5jOecYa2MjspYv6Tb/0lfeKWuHbtDnrb2hx3szs0cfeUDWkkS3+ajXlrVjjz4ia5vry7LmjZW9yBnTV1qyVm/q/ezF+vjMzKamxmVtbFzft5K0rrfZ09trt/rvP1HUs0/8yV/uyHFka5/PnDljIyP97T5J9PMGvgH04437l6ZWo+mudmVV9+nx8TFZiyPd3ysV/XyXK+pnI+/+npg+Rj26PD9sbGzY/v37tx1HrmiSsdVY8vn8wEmG99CXC/VFyOd0Cy0W9DpLBX+3y0U9kSjmdC1f0jXL6W22nO2FoT7GsrO9UD+bW2DOQJroBb3zYmYWO1/RSZyHHO84LNXrDJ0RKmfOZNBpbxVnXyrloqwVCrpmZub9Zf5aJxk5Z52DJhl/tS87858JbO13uVq1SrX/gapU1hO9YlFfH2+S4a2z4kw6zcyqzoTVm2SUnZtZqaRvZqE36faO0Vlnvqxr1SH9UDvs3Djyid5PM7NqVR9/kui+2410uy6V9PXvOONa6oyVgfMYkM/rYxx0D/yrlToDt5kVnHtX0TmOONXLecNB7HzItRPHka19HhkZYZJxPbjGSUbBeZ4yM4t6erI+6Lpvibv6AwBvvGeSce22G0d21j/IBAAAAHDdY5IBAAAAIFNMMgAAAABkikkGAAAAgExd0Re/txw79qgFA/Jw15aW5DITTmhPMKmLU7H+4mFQmdErNbNGsiJr9Vh/UykN9JcLm239RaRmSycaRLH+ItqS883fcl7vZ6+n15lzvmjsfUHUzKzZ1uk2PScVJmhPylrofPsp6jhJEHndNupO0tNKrKNWqgO+bLwlcFLHzMwCJzDAnIzoZlt/gbQXOV/0zfdfq07kxMjsIJtrqwOv/eTYhFwmnd6la3n9RcDd+w7JWrzNF5jDRCegJE19LdpOMkra0l9M3DOlx7V98zfI2vwN+2Vtbo9OyJqZ0ee0UNBjRW/M/8L8/N5Zvazzhc52Wyc6ra3qdKWlJT3e54veDUgPTuOT+vjLQ3o/17dJ3iqV9ficpLpNFQaMB1s21tdkrdvpv4/0nifjyCA77b0f36o6TZ3IaWa2cvYpWTvzqF52fUM/w7z6jXfJ2kjFS5fUbSpwvvj9fG+JV9rXnu/nAQAAAMA3GZMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJCpq4qwLecDC8MBkV1OMup+J6b2wK5RWZuZ1nGWFSeK1MwsCHSsWKujIyTbkY5UTZ11FisVvTM9JzI30dsbndAxkb1Ir7NY0PsSx7JkZma5or6Qna4+b1FPn5uqs878kN7XsrNcL9AxdWGq4317TtyckyZsZmbDQ/p61Bs66jTq6ZjUQV1py+ZGf0xfN9rmAu4UUWSW7z8v3Y4+V82mjj49cGSPrNUbuq10I92mzcwmpvT4lC/oz2duvPGIrN35ypfJ2p5dOm52dHRa1qK8bhfVstP/9DBiQU/HnLYaOk7WzKzjRDNXK7ofjY/pCN/Dh26WtUcffUzvTKD3pdPR/XZ0ZFzWCjrp3NY3LuiimaWm23GS6Auyuqrbcavp3LcGrLLnxHzvdOmgA8Y3jHe+w0DXFs+ccNf7wOf/Utailu63hWHdb1sD7qlbRib082biPDekgb4PPN9b4pX2Nf6SAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKauLsI2iC0M+iNCazW9miN7dKTYZCUna4VEx0vWV3QMoJlZnOi5U6up4/tCJ5pwZGxY1vJO3Ora+qZezjn7EzUd9bi54cRytp2ow7aOczQzS52otuEhHRscdVuyFsb6IAslfd7iWO9r3smb7TgxqEUnezJM/FjHTn1VF2Md5VbSTdx6iY7bXW/0x1J2e/r3d5Jeu229AZHQQU9HsZaKOu54fWlJ1iZndSzsvhfeIGtmZjPzc7JW8HJMndjiqKfHtWPnl2Wt+dQlvc5Qj4ePPXi/rL38Jh0L+9o7Xi5r20UXbjhRkadPLchasaDjzovFEVmbmtYRxqfPPKHXWXZiqVt6HN3Y0O0tX/CzsEdG9DZbTjSnlzrbc8aFUmlAO30eZ2t68fXIXmq67UVORPTCmVPuekeqeryvjtVk7eKqft5aPn9O1nbN79M7E+qbuNeVAi+j/nngSvsaf8kAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU1cVYTtWylku7J+XVJwo0tEhHUU2PVKQtTjRcZa68rRc3skNHbD/WzqJE5vq5M3mUx3jFnd0vGua0/ty8eKaXmekz8BmU8fGNWM/+ne4omMiraO3mXNi7MJAh7zlSjqystXQUZ/Vgt7PvBOv2W7r429FfoRt4oTVrdX1vq41dZuqO3HK7ai/bfTi50eEbafVtGBAnxmu6PYwMjEta7ff9mJZmz90o6xt9vxr/thTZ2Rtw+ln9bU1WVte0zG15xd1TPLIqD5+C/vjjrd89Pf+l6wVvl+PP6971Wv0cgU/Cnt2Vkf/WqrjX9ec+Mmv3vuArOUL+v4zVNNjRc+Jnu7W12TNGbZtenpCF80sdsbg5RV9bkLT0bfevWlsbLTvZ1HkXz/gmbzIau/+fmlFj3UnT552t9lxlq2VdXx4s74ha8fuv1fWZg8clrWxWR2Rbc658ZK+v5WilvlLBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJm6qgjbqdGy5Qfk99UKOjK2XNa1MKczvioVHX0b9fwQ28R0PFia6gjBbk/vT9zVsX9JqmupE1mY5nUU22a3ofcl1ue06cScbheButnQx3FuRe9PIdTrHanraxEt6sjG1rqOCN03dYOszczslbWgti5rnVUdmWdmVq/r41/f1BG2S+s6wvjkGb0/ca6/ayZeJt4OUirlrVTqj6+OcjW5TKsyLGsnNvQ5vu8zX5K1leW6rJmZnVu4IGuFnG7XXn/o9PR44EUs757WQ/XFxVOyNlJyxpg1Hff4+IkTel92T8mamVmhoPd19/ysrM05tdOLOk74sQd1bWa3jv49eVqPPxbpa5h0ncjyvH9vKhd13G4pryPdW2293pERJ9I737+9NOGzRVwNL6ZVt8tzZ8/K2onTumZmdub4U7I2VdP3gr1TQ7J2/rQeJx/8ypdl7WWvH5O16kh/RPRl3zoptS5GGwAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApq7qPRmzU1Ur5vvf0TBS7Mllhqs6pz1w3i/hZTMHqf++h05Lv2MhdMKLJ2s683hoqCxrG+s6b33UyTDfbOvjP3VOr7Pe0e/JKDqnZk/Vv9z5gvNOh+U1Weuken8Kgb6OoyP6vQh33vwyWds4r7O506azvSmdQ99p+uemXtfz8VJBr3d+Vh/jzMwuWbuw0f/ujV6c2OmH/HzxnaBSmbFKpdr384trehw5fka/C+GRhx+StdB5Z0Pc8cYfs9amfjdKznkXRquj3z+xtqlrmw393o6TZx+VtaGKbmNHDx+VNXPe2fHZT/+FrO0/eFCv08yOHD0ia5OTeowtlfW1Gh3R75cIe/p9M42O7retZkfX1jZlLY71e3HKFT0WmJnVN/R6R2r6XlFy3jfVdd7h1Gz23wujSPeznc97NrjWFxd8g1544Lz2KHWLzjEGel+Da/5MWa8zSXRbinq6XW42dR8yMzt7YUXWLji1OJ6Rtb0z+viPfVm/T2lmdresHXn5HbLmPV6HqXOdtnsdlnMZndVu+9x81a5wffwlAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgExdVYTt+HDFSoX+KL18d00uU3IiJKul/hjLLZ2Wjj+LnNg0M7OxsXFZS1OdD9aN9ZwrinTkWnV4WNYWLumYxCdP6ejFS5v6GJvO4e+v6KjDd37bi/WCZrZ3tz6O//eep2Tt88cXZa2X6JjMfKivxebaJVlr1vU5rdWcCMlY57uVy370ZNGJkKwGetlerC/Wvvk5Waut9EdddqPY/vJ5EGE7Nj5plepQ38+Pn3lcLnP+5AlZqxZ0e1hvrMpafeOirJmZBYmO6Fvb1HGzay09VuRLuq1M7dLxixUnXnvPgdtkbd5ptyfu/7ys5QLdb6NYR0ibmV1aWpa1W265SdZuuPGQrM3vnpa14Ve+RNYeOHZa1jptHUveKehrn5iOmk1S/960uLgga8WSjukdHddtw0xHLbda/bHkz+8I2+3yP69ljV9HhK23O86ziPeckpq+fm5MrRtv69U8urrvwAFZqzpxzWZmGw0dp2+BPsaHzugxvZLX/Svf1uPdw5/7lKxN7tEx9ON79XgW9LxXNPhn3GuPifNM5ZSuidNEn73dbDcLAAAA4FsdkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkKmrirCdHp+wcrF/kdaKjmwMA72JelPH1La6OqYtH+hYRjOzZqQjFr1ZVSvSMWZj4zpyrRvrLK+nzurIwpUNvZ9pvihruZw+ipGyXudMvj8W9ZnKKzoK9MaRWVk7P6H358KajpTrNPX5vvdxHWca9nS8ZDTkROON6rg5C/2uMDqq45Zrib7+7a5u42l3Q9YOTPdHvLadPrGTnDhxj5XK/fGhx548LpdZOP+krMWbOsKzNtp/HrccvfGArJmZveimF8na+Us6YvHUJb0/07O6De4/fFDWapM6wvTCqt5euqSjf0+f0vGul9Z0DO1NN8uSmZl9+xEdU9uo6/OWOMm4adeJmPyCjuK98eiLZW3XnjFZ+8KX/lLWFi/ofrtdPGy7pY9jdVWPz5XhMVlLUj0eNpr9baPX8yOId7bsPzcNvo7oTy+K1pz7RpLqaxT1dBsqFvVzQ+AeiI5FdQ/feRYbH5+Stde89vXeWu3B+47J2skTp2Qtdtr28ZyO2i8f0HHy8WNPyNqDn/qsrL3ib+jY7UpVvy7ASdo3MzeJ2I0b7l1jvLOKN77SUYS/ZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJCpq4qwHZucskqp0Pfz8eGKXCYM+39/y9rGqqxFjbpeZ+yHZyWmI/3Sgj7k4eH+WM3L+2O69uhTOm610dHxkuVySdcGRAVvqQzpONXxnI5QvOf4BVkzM+t19TY7ozrCdnpcn5vAdKRs1NPRx82ujrpsNHUUW7enjz9wIord7DczK4ROxF+oY/wKeX1Oex0dGZwOiEUe9LOd6Muf/aTlB/TD/K6jcpnDN90ia5Wu7u833XyjrB09slfWzMzitr6uaei0T1uStXxB95VcbkzWop4eKxqbK7I26sQe95z2dPqiHpvLw+dkzcxsdGRc1g4dPiBrqfOZV2utKWvHvnifXmdLt40XvfktsnbLrYf0vnxFR9g+efykrJmZVZ3oytGxSWdJfc/bcO6jnU7/eXteR9im15jv6a5T95N0m1hQN1I01X3zieM6NrXV0s8UL7hJx0eXSno8C71cVEeS6nUmzuPlna/+Nne9p0/oMeY//d//SdZ6TkT06Utrslaq6vH1Riei/7FPf0XWpvfqMeQFr75D1prmx2AXEr0/Rec6rjTXZa3T1c8iKhZ4c9N/JcIW/pIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApq4qwtbCvNmASNqgoGNqPaWyXq5qQ7KW32ZuFIa6HjnxtqXKqKwtLeq4ruaSjhA8NKEjKzs6wdXKTkzt0cN7ZC10VtrL+dfJi0LM53T8Wa2or9Xk+GFZO3zjPlk7cfrLsnbscR1vV8w7sbCpjkXu9fyuEOaLslYo6vOaJLq9JU7AYRD0t+FBP9uJLp1btlyuP/rwJbe9TS5TKk3L2oROUbTdczpCeWXNj+A7c1xHw3YTHXkYBjoiNJfX7SFOdds1p33GHR2nm8Z6e8OjU7K2XNcxmaHT383MEify07zIT72rNlzW1/HA3LyslXN6e6Hp8eCWFx2UtbGxMVn7w9afypqZ2eJ5PcbumZmTtTjQ43rBiWXf2OiP242inpnp2PWdzGt7gdP0Ui+mNnZi0bcbkp1I0TPnTsvaH33so7K2saHvxXcuXZS1N7zujbJWKunxzDunTpe1njf21GrOkmZvf8fbZe34Y7rt/p+7PyFrG5G+jsfOLcraeKBf0VBu6wbwhY/rsSA/qaOsw11jsmZm1ljT17+Q6HvP+Y2zsra+qdfZbg8ee1pNfd95pufHUwsAAACA6waTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQqauKsG23e2ZpfyRbEHlRVjo2rNHoj9fb0o30/KcX6lhYM7N6U0dTbji1PfP6dKQ9vdz+KR1Td3hOx5s223q5PUduk7ViquMMV9cjWauMTcqamZkt6yzQ+dndsrbW0HGXh15wo6yNjOuY3pHxm2Rt9ZK+FqvrTrybE70ZpjrCz8wscqLhnJRai53YvFBf/oGRil7M4k5SGRq3fL6/rxWcw1tb09GMpYkxWWv29MURyXyXVcZ1zGIpcS5eW7eV1Blx21FT1soVvWAYdGUtCfVyw5M6MrWY6vjeXGVc1szM0qIeR5JAH2MQO/0zp4+jMKTjpSvDutbr6HFk+dwFWZsc0nHK73jrm2XNzOwr95+UtXpLX8d255KsdVr6/jtWG+v7Wber7xE7n+57Xt7s6uqyrK2v6r4Q5JxxwMwWL+lx6/Nf+ZKs3fPw/bK2sbIma51It6EX3vIiWZuZ1nHWOafvbWzq/ry2tiZrB/bulTUzs7m9M7L2nr/3t2XtzLknZe2L9z8ga52GHrOeOKvjbauzernlhx6Steb/liU7/OrbddHMVuvO6xSa+pm6E6zJWjfS8elJMvjG3G45kevPwF8yAAAAAGSKSQYAAACATDHJAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyNRVRdjGQWzxgBi4NNYxnV7sZqVckbXhmo43XbjkReaanTir4/7yTk5m8cKCrLUv6HXeOKNjau96vY5wffKcjsar7dExiVOTs7J28ZKOXhwb0xGRZmZhoo+jGOqotouXzslavrwma5fWzsvaufN1WSsUdNsYG9GRpa2WvvZp3p9vB07ebOLE24aBXi4I9Tbj50da7UCz8/utUOiPFvXOR7uto/kubOhhrDimoxmjno43NTMLCro/tOq6fUapPo58Xkcl93K6Vh0ZkbWZyTVZS1f0WNl14pWDRB9DpaLHbTMzZ6iwJNXbjGOnHxX0StOc3td6Q8c9Bk72dMlpixvOGFupTsiamdlrX3WrrD325ClZe+gRHaNZ39AR4sVCf9x75Fz3naPztf+ezRuLzUmbXd9YkrVPf+4zsnZq4axeqZktbazJ2qrTNkMnlrnc0ffxi8vecXxa1g4cmJe1UkmPS+ecZ62oq+N0W801WTMzq2/qesF5ar3p5Ydk7b7jD8pad1PfcM+u6XtPtajPzd5R/aqFE1/5qqzlSv6zSDinx5j1no4UdoZls1S3t05ncFRtx38Mv4y/ZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJCpq4qwHR0dskq5P+qql9eRePV6W9bSSMfNrW+uy9qp0zpC8Olt6njJSlnPq86f0FFluwYc95Y9e/bL2tjcQVkrbOoIRSvr+My9t92hF1vUcbKVno6bMzOLTV+rRkPXdld13G431scYDA3L2t6hOVmrjekI381lHfV48cKyrEWBPt9mZu3u4Bg3MzMLdfzdUEnH2HVbTkxvsX9/Yi+DcQdJg5ylQX+gnhet2dzUcY8lJ1J1c0PHRHfbzjU1s+aG3mbBuRS1IR1rOD2u4wdHJnQ05fSYPsY4PyprrZI+pyv7dR/rxDpe2iIdk2hmFvd0dGWS6BMXh85Y4UTYjk2M6+3Fel9jp72NjurzXQx0f19zojfNzNJI9/kX36THtbGablMf/eifytqlC/2Rpr2eE/O6Qzz62IM2PNx//8jn9TjuRaqurq3J2lpdP4ucPq/vt2ZmozOTsjbhtLHJKX1PvfSk7puPPqRjWj/xfz4ha6Mjel9yed33Ol3dF7od/czw8T/RNTOzgvPx99zeGVmrTunrf9uLXyBr937mMVlrmh6XHl924qxjPZ6P92qydvwL98iamdnatH6mWHHG0EJXL9fz7r3NwWNoL4rkMs/EXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2NbXV6zX7o8Iy3e9qEdnHqOT0Syf08WmEylnZjZe09FhY0M6xqu1qiNsZ+Z0FN2eW18naw+d1bF5jx/XtTt366jLtTW93K7Dt8laaH70ZLejI27HUh2NtnFRR8NWujrmbPeEc4yxjmws3KojK1trOt7vsx/7Q1k7e8aP980NiJT9KzqWs6UT/ixy5vjhgHi4thMzt6P0ugNPWT7R7XpUd1ubH9Xn/wWHxmRtuKxjG83Mcs7Y1dhYk7V2U49PlSHdH47eqPvD/P69shYWdIR23YnmnN+9W+/LiYuyNjLhXAwzmxgfkbV8XkeBJ05fSZ17RXmoKmu9tu4zTvK0FUJ97dumo48np3Qst5lZXcRBmpk11nT89p5pHWn6zr/xHbL2B3/8f/p+5kVF7xRfvOdLVqn0t8PWRkMuM1TWzwVvf/s7ZK2X6nvRPQ8ekzUzs9Gac69KdIzr3MwuWYsutGRtvaHbV/MJHdM6XtLtfWhUn7fhcd0uy0P6mWF0zOnQZjY6oseQkRHdxyrDeix4/RtfIWvrS3rMfuihp2QtjvS95/Savr6Fgn6eyC/6/XNzVdd7NX1PCytTsnbujH5u2hB9KomvLAqbv2QAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQqauKsA0Ds9yAxK64VZfLpE68Z2g6iisOdMTZqk6BNDOzjQ2dTZh2dEzmbieq7eVveIOs7T36Sln73x/8HVmbHdJRbLmujqk799STep2Hbpa18uQNsmZmNpTqKOLmio60rCQ6pq/b0pF6S5u6NjZ9UNYmZw/IWquuo+9CXbK4qOPmzMyCULfjKNJtKujpmLcg1bVer79rRrGTubmDvPqOF1tlQHzsoZt1/PLCuXOytmdOR78eufGwrM1Oz8iamVku1dd8c3NN1jqRbtdeOxoecqIih3VsbK6oYwsLTixwq6Fjm29/kY7FPXDkgKyZmUWJHqBT53OtXqLvB+mgG8/X5Ar6Nha1dZ9JnCjXMK/3MyjrfTFnOTOzzoBo6suL5nSsZdxdk7VpJzb3Nd/28r6ftdod+/0//KRcZic4eeqklcr9ccjrF1flMjcevFHWKhXd9xYW9L3v1InTsmZmNjyk+6Y7Tmzo+39rzYk4dcaXGw4fkrXD06OyVnMiqS9e1NGv4xO6L+ye1+fbzGxzQ5+bok7GtXKinxtHnGP89rfo57sV59UGF87qtrHU0TtaXXdel+DE95qZ5QM9pu2p6Xvh0K5ZWTt38qSsdZuDnwuTxLkQz8BfMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMjUVUXYBunT//11sRPLF4R6HuOl/aUtZ53bJGdNTFZlbbaq499uf9kRWbvpTh1Tu3pRR/iWejri7dDevbKWOAc5OzMta722Pr7mmo6zNDPr9vSyUUs3ldh0hOKT587K2oMPfUXW7nyl3tfJ2UlZ29jUkXIF3Sxs6oAfqZc47TjuOlG0TmTy+qU1Wets9u9sJ9Lb2Ule8sIjNjQgrvWFL9ERtq0X6SjaoVEd+ecNFWngRJGaWehEik4M6TjA1BnXvE91vEjAnhO3as742+noKMzDN+yTtUpR94dWQ49pZmZp6NxWAl1LnWjGJNW12LmOSaKX67b0uYkTffxh3otl9z+321zW0ZynTpyRtVe/5iWy1ox09Hh1QNxu4EQz7xTNjXXrdfojbJttfU1LVR0Dvb6p2/SpMydlbcwZe8zM4oaORg/aHVk7v3hc1xaW9DpDvc7v/97vkbWkviJrf/6Zv5C1Uw/oaPHJ0f7rs2XxCb8N7pnTY9N6dEEvWND3/4nJXbJ2y9EXyVr3nXrM+p0P/BdZa23qa7+wpp8ZLa/Pm5lZp6vvE/WlZVmbc9pqsaLvdVMzYwN/HsexnfUTnM2Mv2QAAAAAyBiTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADJ1Ve/JSHqxJbn+eUmro3N7i0P6HQr5vM7mzYX6/QI3zI7LmplZuaLnTgf2z8vaba95g6ztPnqrrN33+Q/K2r55va+zL7xF1orT+r0A+eqorDXbOn+5taHz1M3MLizonPbVC/p9F3Gks98rNZ1NPjWlr/+ZhXtlbdfuPbLWa+rjT1s6QzxorMqamVmc6vx1L9+/UtLHWJzVtY1Sf454u7vz8+3NzMpDQ1YZ8J6M4XJJLjNUdYaqfE6WnNckWLDdezK89y+kesxLIqfmvO/Be6dQz3njR+gcRhrodQ6PTejtxXp7caLPt5mZJXqHUtPvegm9A4l1LXbuI6k5DaCn7zFBovez5Bx/IfY/txtq62XTC3qMufSUfjfA3qP6fUtL4YDxMHTOyQ7R7bbNBrSlZqchlzl+Qr974vf/4H/J2mc+9SlZ2+6dIxc29P3o0il9vy04L/iJnLZZnNXPBp/9y0/LWmdDv3vjkScel7XGBf3+nrVLej/HJvVzgZnZpUW93o11fY3Hxyqy1o31cfzFX3xV1ioj+r1c41MzsrYU6XdWNDv6+M4579cwM0sHPBtsqTrnJndJv0NkbFK3m1xu8L03iiK7/54H5XJb+EsGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNtCLm+FAXFWq5s6wjRu67itSlXHjeWcmL2ZyaqsmZmdOb8ma4dvf4us7b1F18x0FG20qWPDRms6Gmz6yItlrZHX8ZIP3/tlWeu09L5sbKzJmpnZ0rnTspaLddxjuayb0Z6DOm721iM3yFov1x9xuqWQG9O1YiRr+baOhmueOidrZk/HNys9Z6pez+nIyuqkPsZdc/2xea223oedZHhk3GrD/dHWaU5HkTY7uv2lHR1N3HGWa9R1XzEz60Z62U5Ht7NeT+dPRpFeLnK212zqMbbZ0NHUvUTvS21Cj0210TFZG6tNyZqZWblYlLU40cdogY51DE3Xak5M9vJFvb12S8eLJoke7wPTx5fEui2amY3UdEzz/n27ZK3V1G01TfS5Ga31jzEFZ0zaKUbGR6xU6r8OkTMWb9Q3ZO2R++6TtQsnTshauM0jVNWJVy6Guh2lXd1uQ9PPVHudePeJmm7Tq00dn3zowFFZOxXr6Pe1FR3hGpfGZM3M7ELDuVc39X1wbUVHPQdOu28HznE0n5S1sKifYZOcc32Lel+aTly5mVns3F+GnP0ZHtXXPzfg1RRbknTw+Y66+l72TPwlAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgExdVYRtt92xMOmPs6qW9GqCso7qKoQ6ei+Nda0y7Efwfde7vkvW7vzOu2RtZEpHCF546lFZyznHsba5LmuXTj4mawubOqbtL/7gD2RtuKIj89odHdloZja7S0dajgyIQtxy4uwZWes652Zi7oCsHbnlpbJmsY6BXFk7K2tNJ055taX308wsSHUbb7d0pFw91VHMaV3H9N00NmA7TvrnTvLHH/uElcv9saNx4dNymdVVHU1YX1+SNScJ2423NTO7cEFvM070iiemZ2RtfKo/mnhLaUA8+JbGypqsPf6EHps26rrPzx/cL2u5gh5HRmr6GMzMDh7cJ2t752f1coec+M2S7ru1st7XZHRE1syJtIyc+08urz+byzn7aWa264CO/y2P6HEtEjGSZmZOUqZNTPQff6mkz9dOMTQ+YuVy//nKO/ep7rKOAV56XN/D5of1fTFwYmjNzDZbeoxvO/fGoKJjmUuBbreXLqzI2j1fvF/WdtVqsra8uiZr6y0dfVt3klhbSzpO+Gm6H+WdBl8p6HG57cQCX1pbk7U4dGLo8zoyNgj1OBE6z8W2TYStpTo6ttHQ12NjQ9fGJ8ec3RHXInBurs/AXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2CZp15J0QLzWgFjbLUFPx3H1nCiuwInHKpecWEIze/FLdfxpyYlmfOS+e2VtdeFJWet0dEzd5qqOlDtz/BFZq6c6Gq0Q6+0N53U02khZx/uZmU2P66i+8xcWZa0X6evY3NQRmmdOnHb25mFZqdc3Za2c1+2mV9LRoss9v01VnEjBak1fq0pex1JuNnWMXy/pjzfsOf1sJ/nkp79o+Xx/Pxzbe1Quk8a6Hd37uU/K2v69e2VtatKPYj131mnzzrWoTozJWjfU4+EFJwr6rjteJWsvvvWFstZ0xqawoIf/E6dPydrjT+ix0MzswYf0ODo2Oixr3/s3v1vWXv3CI7JWTPVnZXt3z8ta14mwDUIdoZk4sdSR+X00zOt6aUyPMRUnDjPJ6WjOQXe7/FXd9a9PSSG0pNh/TtJYX7diTp/DQqSvy76RCVnrOfGmZmabTsRrbkT3hbCo20Lrgo7F76w19b4s6/vmUqLPzVpHr/PA7bfK2uKlZb3OVX0MZmbDw/pZpd3UUcRRQZ+3dkdHBrciPS6HzlhQdq5TGujnotiJqc1t00HDnh5/kkSv9+KlNVnrOcNWvjj4+CPnue+Z+EsGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbrKMLvka//9tZ/2dIRevlCVtdjJzeqajhvbNToua2Zmf/KHH5W1iV06GnXGizts6si1QkHHlA4P6WjUvBN/N+RE7c7O6OjN1uaqrFVyej/NzJYvLcla1NXXqlbWEa7duo4efeLer8ja+WOPy1qnp2MBraDPaeyd771+vK8N6TYelnRMaHlAFO2WcdPn7aYXHuz7WbMVmdn9cpmd4p1/8wesUukfF0ozN8plmps6TvaJB/U52T2r+3ToxIKamVXKuu92E90Gj7xIH8f4bh2j3JzS49rbv/NNsuZFKDecCNtEJzNab1BU+de0e3qdZmYXL+rY7lMnFmStWtXne/GsjsM8+fATsha29b4+tXhR1u74jpfJ2v4Dc7IWxbq/m5mF5aIuFpwoeGccsUAvVwz6r2OxoCMwd4r19bq1O/1jcqepx+mhrh7/p2f1NV0+pdvJ8ZM66tnM7FKk29/EhI7GDZ17aiPR9/g40p261+zIWruj21DPeZ3ApUX9zNCo6+jbNPLbYLWknxu7LX1Og5J+xum19fEXh/T9P42dsXBAG9yShPoYu84zc6ngjBFmViw7z5tVHYtccWqRcz3UfTLtOTeQZy5/Rb8FAAAAAFeISQYAAACATDHJAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyNRVRdgmSWDJgNzDYl5Hw5XzOv7LQh2BleZ0pFjSjfQ6zWxpScdd1i/pWiXa0Ns0fYwT4zpSdmxuWtZ6sY5UO7eg9zM1L25MX9Juz49XzAU6NneorCPles4lznlFJxov7urI4NDJ3txo6ni/bknHjtbm9LUwM2tU1mRtM9FxdO2GnsdPjhyStakBMcWNht7OTlIqhFYq9p+Xx489JJfZWHf6Q6rbUdTV56xeb8iamVkQ6HZWLum+EjU3ZW39kt7XC6fPyNrdf3K3rK1uOtur635UG9GRsaPjOl5zaMSPwj57VsfUzkztkbXyiI73/fQf6+NfeeIBWYude8XxxQuydrahz+mNN+mI4tERPU6amY2Oj8papVrWyw3p9lYo63tTtdp/rbremLxTtAtm6YBz4gzjvUBHgzb0KbTzgS6e3+Zc1rtOfVn3zVxBx782E73O1Lk3tpz7f5o6MchOpOo5J/a+50S/BubHn15a1fdxc8blNNbHUajoWOCRoj5G71UL3r0nl9f3/orp/hzm/M/+C871CJzjSJ12EzjbDIPBz5SB8/z2rOWv6LcAAAAA4AoxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNswKA2MsyqXdDRYajo2baii4/6GalOy1ozasmZmNlnTMV55Z3+66zrSMAn1OpsFHQ22a9dBvU4nXvPorXtl7XOf/DNZ66Y6+q7gRL+ZmbXqetmRmo67LOZ1M8oF+tzU2/o6njivI+zW1vQ17AQ6lnT6iJ5T7xnTbdjMrJvq67+6pM9bse3EAu/R0cetZn9sXqulo/R2ks2VC9Zr9Z/vP//IH8tlziyelbUw0tHEDzygY6m9KEQzs54X+ey060989M9lrVjQ8a8vfsntstYt1mRto6Pb31OnL8ra8vKjenttfXwLiydlzczsxEm93pe95KWy9uP/v5+UtS994fOy1ltflrWNjs40bTlR4E99RccJf/qe87I2lPfj1QtFHYeaK+m2UXMibPfuPyBr7/jev9X3s2bzyqInr2f5IG/5AZHrkRMpWm/ptrCyoceJla5erlfwH6HSnr7e7Za+/wUd/WwQpbpvhqHe3tCovofnck67dO7vqfMxtRvv6mxvu3rovPogdPYncYqhe/z6fMeJE2/r7ad7fP5n/160ugV62cTZV+9Wp+6D8TavRNjCXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2BbygRXz/fOSphMTmCsPyVqS05F9TSeWMlfwI/hKRR1HWijo/SlWR2VtdEQvt3hJR9829+go2pn5G2Tt3MUlWXvhy18ta/VLC7L21OMPy5qZWaO+Jmv5nL4eo040XmA6/u38Ob2vp0+ty1pY0tdiZJeORZ6ecPbTidM1MwtW9DbHV3U32jMzIWt7x3TbOP7IYt/PWm0/HnOnmJ3ZZdVq//m88YCOe06ddpQPdS3nxP2FOf8zljTR40zRGdesUJalubk9svb6N79Z1mpV3a5Hy+Oy9shD98va48eflLXZPQdkre3lVppZzokmf+jxY7L2yOOPy1r1wE2ytrCgj398TNdmijqWujqs7yEri6dkbfnccVkzM7u0pO8V7Vi3tyjR7fj8mh5/7ryrf7lWy49u3gkamw2Luv3j4caGjjBv1PU9rNFw4mSd0zUypu8pZmalin7G8QROjGklr9ttoai358XCFpwoXi/CNk702OtF2JoTH/30srqW8yJeA71gHHsRrjqO1TuOyFkudo4xl9fXIu+c7+32p1zW956Sc41TJ962JKK1t4vavfx7V/RbAAAAAHCFmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgExdVYTtzGRo1XL/vCRaXpbLtGIdcdbQaXOWhjpSa7uIr5GRSVkrFgqy1mpsyFrFif+yrq595XOfk7VDR3Wc4dmz/RGmW8JQZ+pVS/r4ck5ksJlZpaJjOb34v1ZL13q9rqwNO/F+d77kiKyVazo2sJdzIuWipqy1zvgRtuGmjoabqdZk7SVHXqiXG9sla/ecP9H3s3ZXH9tOsrq0au1Kf+z1K19xp1zmzte9TtZKJScO0Imp3S6CL0mdaFzT24y6euxqdXUbXD7bf823rDjxxStLK7L2lBNTu3BRjzHDM3OyZiXdF8zMgqKOsO32dNz5Jz71GVnbf/gWWZuf0LHA5VCPzdWCHn867U1Ze2pDR4EPO2OTmVmc6j68uFqXtampA7LWjHQ7/fNPfanvZ1Gkx+SdYnllxQrF/nud1/fabX3c3a6uFcr6nloo6zhZM//e6EVoh6EeX8yppal+NujFuu2FA15NsKVS1f3Ei9r1cmi96NvtBE6mcGDXFs/cbOpx2Yu+zXuxsM5zmnfevOMz2y4a2FnWWaxc1pHdMsJ2m/28/HtX9FsAAAAAcIWYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATF1VhO3evUUbrvTHuY0GOtLw+BkdDXbhks7U6sY6Nm142N/tRnNd1uJExwTmnDnXyiUd07tZ19Fw7UjvSy7VtdrwuKxdWNSRlWcbOoo1ceLtzMx2Tevo3yDREZqra6uyVhrS13FsVEe/Fp14v44TU2h5HTfY6Oh1dut6OTOzoUQve8P8rKzNzepzeuasjjBevtTfbzqRc9w7SLVasuqA+OLlDd12733gHlmbmdF9ZdfMlKxFkW7TZmarq2u62Nb7mnf6yp6DOhp2flz3h3OPn5e1Rl3Hws7s0m2zOjkma7myjmJttvy4592798na4sJZWVta1uPh7jmddx44kY71jnON83psihLd10pO1Hdpm1jH7vIlXQz1GLRrzwG9zo6OXx10atwEzB0i6nXNgkEHp8fpvHNvECmdT9cqOt5zu8TUwHlUyeV0FG3iXKPYuY97cas5J/o2V9S1sKDPadE5p17Uqref2y3rcbqtG1k+NjYma959ouNEH8eD2ufXeDG12x17r6efN3s9Z7yLvfvd1V+r7e6fW/hLBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU1f1noyRsYINV/tzkVsDMv23jM/o/GUbqsrS0gWd/d52sonNzPJFnfHuLZo47yGIYr0/6y39noihAe8D2NJu6rz5VntJ1rrOfsZOLU2da2Fm9Q19HUdGdFb4yMiorLVaep1Ly/q8DQ/rLPrAybsOejrvuZjXx1DSr3p5elknR/zADQdkrdXU+/OXf/mIrD3w+MW+n/XiRP7+TlLKJ1Yq9B9Lp70ml/nc5/5M1tJI96ORqr7mUaTzxs3M2q2WrOWdz2f2H5iXtRe98mZZO7xPv0Nj7Yx+v8Tiqh4ris74c3hSv0Pj0iX9PqFbjr5I1szMXnjLUVn7H//1w7KWt6KsRc77f7pdXUt7TnB+WV//nPPihAMHD8naxTOP6e2ZmTnvKqg47xS66aYjstZu6ms1v3um72edjv+ek51gYmLCisX+9hKafm9DHOuxOOrpsdV730G7rccIM7Mgp9+HEAR6DEkSvT9d5z6QS/x7vFzOfWeH81zknLdgu5eIOLzXzSTOS0R6Tn9PnOufy+vj995LEXm1RNdC53x779Aw89+j4V3H8BrehWGm22KP92QAAAAAeC4wyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNtcOW/5cv8i5REdPTgxrOcx+ZaOhS1UdDTaxuo2ux3rbVbK/ZF+lxcbEKt5udZZk7ViVe9PIa/PTS6nI3w7qRNhF+kc3jR1IvN0gtnTyzpRkLGTeljI69hAK+pYxrVVHWHb6up4tNExHVGcd+JtQ+daNM2PM72wtClrq3W97GZjXdb+z18c09sbkPzrRfftJM12ywamGzrX7s3f+XZZS7oNWcs5MbXJNpHAqRMHmHPaUtmJ5l5c05GXm2uPy9pKSx9HUNb5y4/d95SsLX/+kqwdOqhjaF9+w42yZmbWbenBouKMB6kTidh01hnm9PibOGmQLScmNB/r871/r46wbdeX9QbN7OYRHc39pXvulbWFUzoat9XQ7T9t9o+x3v1jp6jValYaEDOcxM4FT/X40nHuNxtORHC+4EfG5py6FxtqTqngjJM9p00nXkypE1NrTtRu4Dxv2Ndxv0qcmFZv3E6dz80T75mqpftE5IxLiRMLa6E+N96Z8eKLn15WL1117gVFJ6Y3dGJz8/nB42vk3B+fte4r+i0AAAAAuEJMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApq4qwrZRz1uQDIgrzQ3LZYaHdPRgoaKjuIZKOoprdNSP+Kpv6JjI+sYFXWvqGLeorWu14qSslQs63rXX0RG++bye/xWdqWGhpGPFAieKzsysOqybQ+i0lJ4T91is6AVHxnTU58qKjozddKLoRib0tWj2dEzdEyf96MljD56RtV0TOlJ31159jBbq45garfX9LE4SO7XqZAnvEENDBatW+yNgR51cv9r0EVnrOP2o7HyOUgx0DK2ZWVqpyFppwP5vSdo68nJzc0PWclXdjmYOj8na4eqSrD1x4klZs0CPFYWqjpo9d/60XqeZTU6NX1Ot29JRrJ2OjoJuNHSf6Djxo1FnQE701+TLut/umpuWtVPn9f3FzOzCaX092nV9jE8+fJ+sTU7q/UnHJ/p/Fvn3z50gsNCCAX07cHLau5EeJ9od/cwQOZG/4TYxnl6keupEsXZ7+p7a6elnkcCJTQ28eHcnwjR0lkt6+nx7Ma1O8O3T63VqqbOvsRP/mga6Fub1Ogs5J6Lf4aX7pk5Ebxz70b9uMrDzbBR6z3/Ocr1ocHuLnWjfZ233in4LAAAAAK4QkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkKmrirBdOGNWHZAs21nTcbO1aR3FVq7oCKxRnYprExP+btcbOppwbU3XVpd1LOWqk3CaS3SMXeJGlekoOkt0zZsZehF2ubx/3lqxE7enL6MVEn0de80VWYtb+lrEeR0bt1bXy3WdU7riRBufPO5H2K4t63jNbkNvdHZ0VtZu2r9H1gbtahQn9tWT+nzuFM36cbN4wJiR6PZXCPSAcOGCjv584pGTslbO64haM7Pi6JisTc3oKNa5qVFZ8yItJ0d1/LKTdmnt1qqszczoWNw9c/3xplvOLy7K2uOPP6p3xswOdA/Kmhc3vLmpr2OzqaNhN9Z1LLAXYRt39XiQKw3J2sMPTclat6PjTs3MZmZ2ydqeW1+kl5vWy01N6zGmPOA42p2dH4OdJIklA+JKO87596Jou119Trxr2o2cG6OZJU40aOAEueacaNxyScdLh3m9XOzE4nqRqoPO85YgdCLznePzYnHNzIrbRAMr7ba+jj3n+HPO/njXwjtv3ljXbOqxJ3Aies3MymX9vO0dR6+r98eLty2XB7e3wGnbz1r3Ff0WAAAAAFwhJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNXFWEbFyYtLvTHWUXFl8llOokTm9VbkrXyqI7xGpvWEV5mZuOhjiqbaOrYrbUVHWm5tqRjzFoNfRrjno7FtVTP8ZKe3s92S8e0FYt6ezkn3s7MbLOtt9mq620WUh3xVwtrspaEOnoyivQ5LQ3p2LjygPa5Zayo9/OQjcmamdktt+lIy6O33iZrB264QdbueKWO4j270B+92en2zL56Ui6zU6Tdjg1KfQ6dzzzykW67IwXdbu/5wqdkbfGCHn/MzAKnLd1xx0tl7TWv0uPh+rqOaX3gq1+UtYYTzfj46TOy9tTJk7LWaur2l6Z6/C2PTMuamdnGxqasba7qc97Y0FG8XqhjPqero7WqrM0d1FG745O7ZW1mTkfGzr3kFlkzM5sY0eOIF9vpxWha4NQG3GPyTjz4TtGLegNjUL2YWi/C1Jwo0rwX/e5EuJr57da7pl7Ea+rE1EfOMXrH4cXpB6bPTS6n21LoxdtuE9PqRcOmTqSu9/zjndNrjb4tFPTxX+v1dV9tsM3+FEXcrJlZtaTHQu9qqGu1XQzx5d+7ot8CAAAAgCvEJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTV5QutfVN/2Z7cHJDS/zczCwoRLKWJPpb8mFTf98939DrfHph/e38RksnEzRaer1NL3mprZMQnEM0b47npkt19H7GTipMbpvUglZHH0e7q7eZprqWd5K+2l1d63jnLXDSLlKd6NCJ9Eq7Pf/cFJxlVb8wM6s3dGpFy7mOnQHnZmv/veSN69nWfrfagxPnIqc/9Jzr2hbrMzOLnSSSZJvzGKR6WS/Fpd3R+9Pp6LbS6epa1+l/XtpI4hy/l9LipUslid9XEtN1f5vX1q69xbzj91JcvHPqJRh1nGtvZtbu6HacOGk8WaZLtTtPj0k7cRzZ2ueu6Cvq52bbXFOnf0U9fZ56240hTi2Jddv006X0OiPnPuYlOsVOn04T5/km1usMneewb1S6VOwsFzvXvxdt80wpeEdxreNLsl26lNM2epGuRU5K2LWkS0VfO2fbjSNBegUjzdmzZ21+fn67XwPwTXDmzBnbu3fvc70bV41xBLh+7MRxhDEEuL5sN45c0SQjSRJbWFiwWq227QwUwDdGmqa2ublpc3NzV5xRfT1hHAGeezt5HGEMAa4PVzqOXNEkAwAAAACu1M76GAMAAADAdY9JBgAAAIBMMckAAAAAkCkmGQCAzJ08edKCILD77rvvud4VADsU48jOxiRjh3rPe95jQRD0/Xf8+PHnetcAXGcGjRXP/O8Xf/EXn+tdBHCdYxzB1bqil/Hh+vSWt7zFPvjBDz7rZ9PT08/6/91u14rF4jdztwBcZ86fP3/5f//e7/2evf/977fHHnvs8s+Gh4cv/+80TS2OY8vnuT0A+CuMI7ha/CVjByuVSjY7O/us/+666y77B//gH9j73vc+m5qasje/+c1mZvapT33K7rjjDiuVSrZ79277J//knzzrrZObm5v2gz/4gzY0NGS7d++2X/u1X7PXv/719r73ve85OjoAWXnmGDE6OmpBEFz+/8eOHbNarWZ33323vfSlL7VSqWSf+cxn7D3veY+9853vfNZ63ve+99nrX//6y/8/SRL75V/+ZbvhhhusVCrZvn377F/+y385cB/iOLYf/uEfthe84AV2+vTpb+DRAvhGYBzB1WKK+Tz0n//zf7Yf+ZEfsc9+9rNmZnbu3Dl761vfau95z3vswx/+sB07dsz+3t/7e1Yuly//efMnf/In7bOf/az94R/+oe3atcve//7321e/+lV78Ytf/NwdCIBvmn/yT/6J/cqv/IodOnTIxsfHr2iZf/pP/6n9x//4H+3Xfu3X7DWveY2dP3/ejh071vd7nU7HfuAHfsBOnjxpn/70p/v+4grg+YFxBM/EJGMH++hHP/qsP09+53d+p5mZ3XjjjfbLv/zLl3/+z/7ZP7P5+Xn7zd/8TQuCwF7wghfYwsKC/czP/Iy9//3vt0ajYf/5P/9n++///b/bXXfdZWZmH/zgB21ubu6be0AAnjP//J//c/v2b//2K/79zc1N+43f+A37zd/8TfuhH/ohMzM7fPiwveY1r3nW79XrdXvb295mnU7HPvnJT9ro6Gim+w3g+sE4gmdikrGDveENb7Df+q3fuvz/h4aG7Ad+4AfspS996bN+79FHH7VXvepVFgTB5Z+9+tWvtnq9bmfPnrXV1VWLosjuuOOOy/XR0VE7evToN/4gAFwXXvayl13V7z/66KPW6XQufzCh/MAP/IDt3bvX/vzP/9wqlcrXs4sArnOMI3gmvpOxgw0NDdkNN9xw+b/du3df/jkAXI2/Pm6EYWhpmj7rZ1EUXf7fV3qjf+tb32oPPPCAff7zn//6dxLAdY1xBM/EJONbwE033WSf//znn9XRP/vZz1qtVrO9e/faoUOHrFAo2Je//OXL9fX1dXv88cefi90FcB2Ynp5+VpqMmT0rq/7GG2+0SqVif/Znf+au50d+5Efs3/ybf2Pf9V3fZZ/61Ke+EbsK4DrFOPKtjUnGt4Af/dEftTNnztiP/diP2bFjx+wjH/mI/cIv/IL95E/+pIVhaLVazX7oh37Ifuqnfso++clP2sMPP2zvfe97LQzDZ/0TKwDfOt74xjfaV77yFfvwhz9sTzzxhP3CL/yCPfTQQ5fr5XLZfuZnfsZ++qd/2j784Q/bk08+aV/4whfsAx/4QN+6fuzHfsz+xb/4F/b2t7/dPvOZz3wzDwPAc4hx5Fsb38n4FrBnzx772Mc+Zj/1Uz9lt912m01MTNh73/te+7mf+7nLv/Pv/t2/s7//9/++vf3tb7eRkRH76Z/+aTtz5oyVy+XncM8BPFfe/OY328///M/bT//0T1u73bYf/uEftne/+9324IMPXv6dn//5n7d8Pm/vf//7bWFhwXbv3m1//+///YHre9/73mdJkthb3/pW+/jHP2533nnnN+tQADxHGEe+tQXpX//HcoCZNRoN27Nnj/3qr/6qvfe9732udwcAAAA7CH/JgJmZ3XvvvXbs2DG74447bH193f75P//nZmb2jne84zneMwAAAOw0TDJw2a/8yq/YY489ZsVi0V760pfapz/9aZuamnqudwsAAAA7DP9cCgAAAECmSJcCAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZCp/Jb+UJIktLCxYrVazIAi+0fsEYIA0TW1zc9Pm5uYsDHfe5wOMI8BzbyePI4whwPXhSseRK5pkLCws2Pz8fGY7B+DanTlzxvbu3ftc78ZVYxwBrh87cRxhDAGuL9uNI1c0yajVamZmNjtdtjDs//SgXCnLZb1PG/JBTta8mVEviWXtaxuVpfWNTVkrh0VZq4Z6X+udtqyF1ZLeXrEga0NDQ7I2MjIqa2trq7LWbXZkzcwsdWpRN9JF5wOlXF6ft2JeX+ORId2mZqfGZG3h4kVZa3Z1u6nV9DrNzHo9fXaajQ1Zm5uryVqhoLtfPtdfi3qx/fGfPXq5P+40W/v9Wx/6A6tU+9t3kiRy2UpR981CWbeVNKf7Xy/1PwnNmzM+OUNQQR+GWarbUer0hyjweqcWxM5yqR5/4kgvF3sHb+aOB57UOzdOzdtekjjH4SzonW1vXxJvP80sibc5d9ewPz33vPU3xlazYT/13rt25Diytc+/+v/5gYFjQqvZlcvmcrp/BXtnZW3deb554Ygel8zMzj78gKzd/SVdW+/0ZC2X0+3We94qlPRxjE9NylqtrM/b4b1TsvaaV75U1uLIeZ4ws+WNhqzlnXv140+dlrW/+PSX9AadsbdUcJ5T8noMLeZ1X+86x9/rbTOADujTW0rO/a6V6r6x2tZjSCh2tRfH9mf33LftOHJFk4ythhuGwcBJRs6ZEHiN3lvOm2Sk291wnW0O2v8rqfn7eo3rdAY9r5Z3HtzddW7zp3HvrCbest4kw1nOPUanVnCO31sul9NH6J1TM3MfDr3j8PbVPQ6ntlP/mcDWfleqQ1a92klGSQ+eRWeSkbiTDL8/eJOM3HU0yfD6bXiNk4wek4xr2hevDZuZxdfBJGPLThxHLo8hxeLgDx6cZ9ec078CZ3zpOOPLUMWfZFScDxILOe8+pq+bO1nyPtR1tlfI60fBovOQXS7p4xuu6vPWi/z7bSvSk6yCM+krO9fRO0ZvklFwakXng8Ji3utfzkP9dgOo06eLAz6c3NJzlivknf3Z9nHb39+d9Q8yAQAAAFz3mGQAAAAAyBSTDAAAAACZYpIBAAAAIFNX9MXvLYVcbuAXmeOe/rZVEjtfPHMSYzo9J11huy/pOl9EGatVZW3ESXTqbuq0g6Slv7VfLVRkbbSqa1Xny03DzpfJllo6QSpJ/XSpcll/aWp6WqdIrK7qRCsveWxu94ys5ZwvRs3MTMia96WwE2cWZK1Y8L+8NDam28awLtnkqE4CC5wveDWaA9qb05d2kiR4+r+/Lu98ibDrJMo11nViXGHICV5w+qaZmTnpU4lz7XrOl7Tjth4r2+stWSs6fTM23S7qrbqshYFe5/CQbrepsz0zP0HJ+5LgtX7Z2ssB8b747V1D73vm3pe73S+om//Fb+/cJM7Z8RKtBu3rtX75/HqytnDK2gO+dJt3xkjvy63nnHvjEy3dZ2+96ZCsmZklXb3eXVP6nlpxtun1FK8NNTt6X9ZX9D28Huj20mnrMeu2218ha1FTJ3KamS0t6/3ZVdbjdtLVSY+VkjcW6HYzUxuWtRcdukHWLl08J2utlr5n1et6zDYzs1DfJ0t5/dw8N6vH9Kion8WOP3Jy8DK9K/sbBX/JAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNXF2GbDy03IMI2CPRcZXxqUtYarabeVqxjantOvK2ZWeBE+u2e1VFds9N6X08cf1LWpvI6Gmx2blbWQicCLHSi6EacmNbJ0ZqspTk/snPUiVutDuno31yor8f0Lh3TV3aieDc31mWtl+p4v9ExfQx7erpd5LbpCfmCXraU01GgSVfH/43URmQtjfoj9bq286Mnzcw2G3XrDeijUaSv69KlZVk7e+6irOXKTvRwbVzWzMxKob6uTrqtdb1I70j3leamji6sFPS+WKjjFze7Oiqx29UHcejgjbJ2w+H9el/MrFLW45MX/+rVnLRZS51i4uXbeiXnHrJdTO218uJHQ+8Yt4kUfj461SlaMe6/fzRb+r5RDJzY1FjfN8JAR+0vnbqg12lm9yyclbVjF3VMa9rR44TXTspO34t6zv0j1M8i5Yoee9Zauu196cEnZG33pD7fZmadnhcp79yLnft4wYupd7rQ0cOHZe3APj0Weq9LWDx/Uu9K5Mf7Do/vlrXYiWWvlvT9ZW5Kx/SeyQ0+jiD1n8O38JcMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJApJhkAAAAAMnVVEbajtWHL5frnJWUnUnVmRkfGXlzWsZTlko5NW19dkzUzs11T07JWKulo3EpFR6rumddRtENDOiYz6uqYr6LpaLxSUR9/s9WStfk5fb7Tgh91WCzp/el2u7I25cTR5Z14zU6nIWu1ER3/1uro499c17GAnY6O8Juc0tG/ZmaVId1V8oFeb76rz2m7oY+j1+mPQY29CMId5Itf/pIVS/1jRr2hI/ZC032z1dGRhu1YjzGFoq6ZmeUS/RlM7KQhtp1ov9iJVB0q6nG0Euj2V3bGtDjU/bbR0FG7X3ngXlm7uLQga2Zmhw4elLWpKR1pXanqPp8m+rzFse4XSarHn8C5vvYNiqn1pE6Eb+rElnqRuoNigd2o4B2ilQsszvWfk5VQt4Ug7sjaZF73r+ERHXXdbujIXDOztU29zY227n+pcxxee88568x7nylHug01uvoYhp2296X7H5C1IzfcoPfFzF5weJ+s5Yt6nDhwQMfNNhJ9D7lw/pKsbWzq+7Q5Eekve+2tsnbflz8la61tXtGwGenjX27otjrR0tG4e3I66rxdHzz2RG7M8F/hLxkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABk6qoibCcmJ6yQ749L9CLxum0dm7VrVsetVssVWSvldGSjmdnuaR1hG0VNWVteuihrtREdcZov6Lla0tXnppDXEWBhqKPhWs0NWTMnVSws++et09VRbR0nxq7kxA3XN3Q02tCwjmLzYvqWV3RMbamgI+WcFEjrOsdnZrZZ9+JV9Yq7G/o4ul0dNzg8IBY5ep5E2K432lYYEJmYpvo8Bqb7Q76oowmrTvRrLvSHPy9ium36WvScz242mzq2udXQtVKg++5wqvtfzjnEQkmPse26HrefPHNOr9TMTp1flLWxER13Pb93r6xNT03qdY7r2MZ8qM9bzom39WJhPfE2iyXOWOFtM3X2NXEjbPtrg36205SCVSsO6Nu7qzr+c8yJwZ4Y133hROrcwyp+HHDJiaz2xqZoSPfpqKfvG+2Ovo/FzrjkxUcXS/q8zc7vlrW5vfOytuSML2Zmixv6WeQVr7hD1lYu6LHne7731bL2sY/+iax9/nNfkLV9L7pd1t5460tl7clzT8naic9+WdbMzNa7+lm03tPt8aaX631tRfqZampqcLR6N9Lx6M/EXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2IaWDIzr7HZ0HFnsRIP2Qh231WnrqNl8zp8bbaytyFrgRE+mTmzqufPnZW10WEeKVfM6BnOjs673xYklLJad6Dsn3i7aJqY1CJ0oXic+NcnpWsmJF3VSSa3Z0vtaLDlxewUd/Vct6/jIUklfJzOz9bU1p6av43BZR3YGThRzdUDUZzfS8Yw7SbubWM/6+36h4A1HTvRnrNt8aroWOO3WzMxJn7RupMe8yDmMWnVY1jY39Ji34cVLOxHixaJu17WiPsBcTi/X6PnjSC7R40hnSfeVtTUdEz00rCNGd++ek7XDBw/J2nBRjxUl57xFkTPG+ommlpru88k1Rup6abuDInXj9Kpu+9elQjVvxQHjxaGajsU/6Bz3aHFwTKeZma2flaXqmG5DZmaNou7TSUGPPy97sY4b3TWjj/Gp48dl7cxpHT0d5vR9Ou3psa4c6mN41Sv0MVzSp8XMzL70qb+Qtcce2ydrcctZ8ZCOul5r6DGtHunx7Pj5ZVlrJLqvN3p6nRfX/PG1U9b3kBv36/FubJceJy8t6+N44xtfOPDnzVbLPvDHH5bLbeEvGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATF1VYHZgqQUDXm5QLOrVePnePSffvtPWufDjlSFZMzMrhDpTPx/qPOh2V+caF0s6R7vb6eraRkOv08l+9/Ltg4Lez9jJsK+U9fbMzKKuvh61kTFZK5f1uQkCnaO9Wde5+FFXLxc478Lw9sWcfPtO08+mjrt6Pl7M69zqkYkJZ3f0ey82Gv1535HzrpKdpNVtW37AuNBx8siDQPdp75o7rxCwVK/SzMwS50UZXq3R0O26XHHe1eL160gv1+7osbIXOO9ecI6hGOp92f6jKb3efF6v19ufzaY+p+tPPCprS8tLslZz3mGzd89eWRsf13n7xZI/xnrve0l6ejzoOe/f6DkXJE77x4xOqsfBnaLRLVg04L0Xozn9bBAtrcramTX9DonX3PYCWWt19f3dzGyPc93KVd3eXzmmj+Pm6SlZayZ6nUslfd9srutzE+vHG8t3N2Vt/+kTslZZ89/5NDE9JmvRQ/fKmve+j88/oseJxxYWZK3tPFOdO63foXJx+ZKs3fGSV8ra/rF5WTMz+/f//Q9krdtalLV7vqzHwgsXnpS12+8a3P7zHf+ZaQt/yQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTVxVhG4ahhWH/vCR1YtMqQzrSr+3EKxaHdIRb3NgmOivQhzW7a5es9ZadwMueznEbKupouM6mjl4cndXxps1mf4TplZjaNa33pe5k0ZlZLtDxbwUvNtaJbWy39PGXinq5sKhjYded6x9FOuY1F+vYvHZ7m1jHREdvVpwI1bwTRdyO9PW4tNQff9eLnTzEHaSbppak/ccSOMeXJE7Niax2lfzl0pz+DCYJdVvKO6Nq1NVxs8W8bkfDFd2Omt22rPVM72fHGe46PV0shf5tI2dOTK3zuVaUOBGupvv1oHvSlsWVi7K20FmWteOnTsvatBMhOjfnx08OD9dkrezEpKdOpHCUOhG28YAI27ZuLzvFVK5kpQFxpXuctjcyos/9fas6inS1sy5r+2d3y5qZ2d+8eFDWCk68/eQTen9KT56XtTjR97EDznBXiHUxdMal2Hlm6Hzpq7I26sTCmpklU87zn5fnvKHHiZGcfqboNPS1mHDSvKupHs83Fk/J2p6bjshabciJ4TezOw7vkbWL6/qZYrGunymbzRVZe+qJJwb+vOW88uCZ+EsGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNvzSxuWGxDrmKY67nCoo+PGhkd1TFm7q6PIhnN+xNee3eOyVqrqqLbcql7neFVHSI5V9f7UZnXcYSfU5+3xxQW9vbERvc6GPoh2U0dEmpkVnPMabTjxrx0dR5cEOv8tV9C1en1T1no6Nc66sT6n02NVWZsY0W3GzOyJzadkbXJcL+scvo048c5J1B+3GPV0n9hJ4jQxGxBh6y7jxJu2nbaSd/JkndTGp5cNdRxg6sVBFnQx7w25TkyvBbpdDxd1jGTP+RgpcWqRsy+92I/CDgO94tSJn4ydmNo45+TtOt3CuTVZ4MRv9iK9nxsLeow9df6k3qCZlYp6jK1W9fhUdmKyS05MdqHQf4zdjjOA7hBHhqtWGdDuh5aX5DK5UF/TI3v3ytrmhf448cu8gcDM9jj9tlp0nkWcSNHAeWWA1zM7TtSzOTH8BacT5Z3+XAh1xGlUc26MZpY29TNFz8nejk2f013OeP7Gin4W7Qa6f8Vz+pUI5ZMnZa2pV2nmRC2bmb3wBTfI2u6mPsbdkb6HHjk8J2s3TA2O/m20Wmb2/8jltvCXDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADJ1VRG2nV5ig5IEV1Z03Fq12Za1iUjHbRWcXSsP67gxM7N2c0PW6l6Mq5NGl+vp5TqbOm5tujY4/svM7LEnTsjacFnHGQ5XdPRpx4knHN89IWtmZkHsRDo6kXJlpxVttnW+ZKmkYxkXL+gIX0v08Q+Pjslau9WUtV6k4/bMzCplHblXG9J5dCubdb0/Hd03asP97SaKnh8Rtp2oa4POZhDoDpg4sY1ehHbP6Q+tjm4PZmYFJxo258S0lvJ6uTTQkY9BqttY4kTKpoluF85ps2asx7Su6e2FoR8/2XWuY8GJ/EydiNEo1MfoxdSGOWdfA93/vLRPZ3OWeLnAZtZt6fFgo+H0by82uKPXOahPxc59d6dYXTxprXz/te30dPtq5XT7ao7q+3Slqe8N7UeflDUzszinr2lvSN84w5y+RiUnNjYwfU/tOX0v9saXATHIl2uy4tfyM4ecqlltTfejtvMGg+5+HSc/3tP9ZKitz3dvTY+T9YvrstZc+Kysnf/K/bI28sIjsmZmtryoI5W7Vf2M50X/N5d1LPdGYfC5abb1+PlM/CUDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATF1VhO30+LDlB8TG9do6Gqw2XJK1tKdjw3J5Pf+pVHRkqJkfadhs6W12e04spZPTetPRG2RtcfGCrHU6ekenpqdlrRfrSL3EdNxcdZvo325Tx9jlKjr+LufESzZWdMTbelPXRkdGZK3e1OctTvS5KTlRfJETUWxmtmffvKwlTvbx6obuG14s6dhE//UPI38fd4pWu21h3H/seS83NHGGKuc8thq6/xWLXsii2cSuvbJWcdJGQycaNueMXWmo2+766rKsteo6snv/waOythnp8WB1VffNUknHa5uZRU5EamBe3K5zPZym7y0XO6ssmj7fYU5vsBd5UaDbfG7nRB+nnYasJWtnZG353FN6e2n/9rxxZ6dYaaxbKdd/bGcaOlazl+hrWgxmZa06PiVry61NWTMzm83p559KW7eFeEO3zU7XiVuf0vs6dEQ/p7SdeNf6kh5fSonzXNDRsfedS/55s5KOog3GdNxwPtAdPtnQbaPyQidSt6i3V72oc2Eb587J2tqx47KWnNb3LDOz2kRN1lbGdN9eXtTX+PzFs7J2sLh74M9bnSuLwuYvGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGTqqiJsh0o5KwyIsL3p8D65TKWq4w7DnN784pnzstbr6Wg0M7Oh4RlZW6vrGLNcoOMlAyemdHNdx7Fdurgka5GTRGdOFG297sSipnqlzaaOSDQzqzsRbyNVHZvWdaIg08CJ83QiS0dqenuVqm43gyKWt9RqZWdf9HJmfuzjidM6XjLI6zZVzOltbjb7r0X0PImwjeN4cLtw4kbHSxVZGxnSY0zLaSsW+BF8hbqOJyw7cdczM3r8aVd0G+z2dD+qlPUx5qr63FSdKOixocHRhGZms1N6jN0uArXtRMo2nWUXL+noxqixJmsFZ8zL95zxPtHXP4r0mJ7P6WuRmL6+ZmZJ6LRHJw51Y+GkrHVW9Xmr1/uvY+pFBe8Qa+22FQdE2C429b0x2tD3v6ldOjI+ndf9uTSu71NmZqUNPWbnFy7JWrfelLW66T4UD+uxoLBfP6flAx0tPTSm9yV6/LSuOVG7bSeu28ys9tqbZa25pp+p7LFjuuaM2XZer7OTrMlaYXZO1mZf90pZK1X0vX/l8SdlzcxsrKmXHd2vI5NPO69TqOT0mFAoDH6GiZIrG0f4SwYAAACATDHJAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZuqoI2+FCzgqF/visoeqQXKZQ1FGso2MTslbRibG2urysi2b28KOPy1ov0fOqUnFY1iaGxmVt4dw5WVte0tFo7Z6OO9xwYnEt0MeQOumSa2urumhmkZPo2e3oYrWqI9UmJkdlLXCOo9PTkXqpE53WauvY0dR0LGev58fDdjp62TjR+1px+oYnPyA2Ln2+fCbQ69qgvNpRJyZ5zImiPXdexyi2ijrSrxP71zxYPCVrByd1rOXM/B5ZO7awIGtpoge9akO369EhPY48eOZ+WRue1ZGewyU9bp94/BFZMzOLnbFy7MZb9TbnbpC1xqlHZS1X35C1kVRHmjbra7q2eVHWigV9n9ho+1HYlTEdlTrp3PTqTky4k65uwaCY8DQ1i/WYtRPs2TNn5UL/mBCe0Pfiiu5CFnf1PaUU6L6w2tBtz8zsc2fOytpcW9/jX2B6ZztONGzLeRbpflX325aTHx7s0eNZ+8isrDV7Our51sM6otbMrBHqPtZy4pyL6zqyujei4+S7p50o3gt6nCzM6HGiuUvfIwoT+rlo/K7bZc3MbM15vcPYlB5/bh/eL2uf+Ix+NiyJMStu63P9TM+TpxYAAAAA1wsmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU1cVYTu3a9pKxf5FvAjP8TEdZ5gLdNxWYUovNzs9KWtmZn/2yU/JWpLobY7VdBbg4nkd17VrXEdIjo3qKLa1izqmbuniol7n+IisDQ3pmLZRZzkzs9qQjhSujerItaFhHfHXa+ljfOq4jgjN5fVxNJ043W7XqXV0O83l/Pl2YDobuFLWMamxE38YRTqKMOr0t7co2tmxk1vCOLJwQFebHdZ95cKqjgqMnH6br+lY3NAZf8zMepGO9dt/+wtlbdVpK91xHeuYC/RwHI7oMWZtQ0dhbjqRzklzTdY6bR3vO+rsi5nZmbqOjW1c0vHj+8fGZG3uqI6+XXtEj82Nc3qMWb2gaxsNvZ9xT48V6y0nT9bMKuM6wrY2r2u9po5Kbbd0vHYY9rfxVKeV7hi7ds9YZUA8/uY5HRlfHfeyfvUYXhg0WH3N+SU/Tv8/3f+wrB2d1OPdj5d19HnVuVWlDd33Vh7UEbYr0/r+/lRHR7h2nejbuSNzsrZvXG/PzKx7/oKsDTsRrkHi5PBv6utYCiuyttFqylr81FOyli7oZ7jVmm5vQ0f3ypqZ2dzBw7LWXtTnbdqJ03/Ji3R8+PzBwftTbzqZ0M/AXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2KZpYmnaH89YGhAlt8WLBo0aOhqtlNNxY2nBjwmME73NMNT76s64Eh03un//QVmbmtaxhHvP67i5Uknv58iojiLLOeft4sVzsmZmducr7pC12TkdR9dLdYTkxvIlWVtd0hGhy2u6beRzOjZvekpH4yWJXi6J/XjYUSdedXVdR4imTvxht6XPWxz1R4jGvedHhO14rWa5Qn/7nhrWcbNrKzqab6Ks+0rJGSt6A87xM80cPiprh3bPy9rDp3Ws4VhJRzP3Ih2/ODM7JmvhlG6bjbwzFtb0vqxe0vGL+2f8iMVmUR/Haqz79cqqHivC3ftkbe/Nr5S1c2ePyVrbiaYsePefWI8jOec+YWbWWdNRzJdMjyO9pt7X0LnHbjOs7Vjr8Zp14/7Hl3y6Lpcp5PXjTte5p6z1dFTnSsvPA+6lepsbBR2beq6go67HUj1udUNdS1Mddbye6PZ19qLusyOhjrNe1Ydnf3juD3XRzI7u2SNrhyf0NidLs7LWOKmff+KWPsY01ud01RmzvHGi68TeR+s6htnMrPvAE7JWdSKFO859cv/NOpI9Whgc9d1r6+eXZ+IvGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGTqqiJsz547Z4V8ru/nw0M6UnVzU0eDeXGOXdNRgHFeR3GZmVVrOgqz29JxZDPT47JWCnWM3eFDOm6t5Bxj6ETYFZ0I20rFieF1IlPTlo5INDPrbOhI3WhUH//kbh0bGzrxf/vndRRmqbwhaxuNNVkrFnWTzge61ov86MncgHa/Je7oyM5cWfeNtKcjBYeHJvp+1u32zOxRucxOMb9r3ArF/n7xPd/5RrnMqacOyNpmW7fbTltfm17Hj7A9MKdjU1MnDjmd0jGK605MbaOpj2Pv1Iys9QbEim+pN3TMYOrEKA6neizMJX4u6q5RPa41LurIx/o5HaMZdfQxDu3S48jcC79N1pJIx51eXHhS1pp1Zxzd5tyMDOlxJG96rHSSUC1q6m2m1n8/SFM/dnUnKKaJFQe0+7wTITzlxNd3c3osyDt9ttnW7dLMbI8XYX9Qx2Cfq+u2YM71KzoxpUHPifBN9L1o9+SUrOWdIXTDicFOV3RfNzNbWNbPjetV/Uy1r6Ovf7jkRPg7z4VhT38W3+rp/WzGut2kTvRvteW/ouH8ubN62UAv2+jpYxxz7oVTtx4Z+PPEee55Jv6SAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKauKsK22epaId8/L0kGxORt6fZ0vN7EdH9M5+V1JjpSq93240bn53U03CMPPSZrhbw+jt2zOopu2om+zQU64q7gJPEWS/rSVKs6/iyXc+LPWjpa08ystaFjY1cuXZS1NNQxmZWy3h/vOEZqOqZvo7mi9yXWbaNS1tGaQV7H4pmZRU6M4UilKmux06ZGnCi+wqCkS51+uaPUcm0r5vr7xatu15Gxd7xQx0RvNnX8YpTqz1Ginh/l2WvqGMlWW2/zYFfva7Ojx8N6Q2+vUNDjwarTb8sHdRtrdfQxpGM6tvLc4nlZMzN74sRpWbt5XEfxnr6k+7UlToR0WUeWD++/Xda+7fABWVs5oyNsH/vqPbJ2cVHfX8zMhoJVXezoOMx2rI8/SPQ9Jj9gIEnT1DrOOLkTVNpVq8T9fWKhp+PUZ5z71HhrTdbyF3V7720619PMbrr5oKztO3qjrK3cr9vR7sC5ERT0mFZwxsJKXbe9vOl1Vqv6nvr4kydlbarhf7596IB+Njxb1G33wnF9rSqbenwJnHtB4PS9thN93A31MXYbermV2H/VQLU6ImubXT2mNzr6GFfOXZC1/L7Bz43N7pWNIfwlAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQqat6T0aYy1uY688M7rT1OwRKzvsHOk6mb6ms5z9hpHPBzczirs6b31xdk7VmXefNH9x3WNYqJf0uhOGqznAfHdcZ01FPZxDHsT7fuZw+b1NTel/MzC5e1OftvJNhf89DD8jaDTfodx9cvKTP98L5S7LWM91uxkb0MRZMt5tSSb+zw8ysl9dZ2Z22zl9PnNeWVCfGZG2jXu/7WRz673XYKRqra9Yd8JKYsyceksvs3aPz5vfs3iVreaf/JYE//G0sLcna2prOx5+cmJS1Rkv362ZL9+uGk2O/WdfvBjh6+JBeZ8N5L0NLjwXTlZKsmZkVOvoYX/qKO2VtpamXO7m4LmvdUPfduKX7po3rdx/N3arb2/St3y5rvVWdN29mtvLoF2XtxENflrWlJx+XtbCor2OY7x/z0jQ1u8KM++vVeiOy7oB3QvzFun7/QE93S3t1ovte5eKirJWjpl6pmb3kpW+Utbn5G2Ttj770oKytd3SbjvP6ukbO+zUqqb5Rtc/q489N6PdZHBrX79ppx7o/m5nlh/Rz462vuUPWVvSjga3co9/11Un0vTXJ6/Gu5Zy3oSGnwVWG9DqL/guxkkn9Xra28zKtRecZbn1N3+tWjz0x8Ocd5x14z8RfMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMjUVUXY7prcZcVC/yKlgp6rVEs6iqxS1fFfPSemteDEjZmZjZR1jN3hPTrucqyqI2XnZsZkbbikY8NGhnS8YjvU2ysm+rxtODF95SG9zkK1Pzb0mRYv9cembjmzoqP6HjuuYxsXL+q4vY11vb0o0rWbb9ota8NlfYxx08m3S/zYuDTVba5cdLbpxLwFOd39enH/NR70s51otFy1YrG/fW8u66jE84mOH56a1ePIqHOOh2pjsvb0wjr+NhfoqMia7oI2OqzXmYa6z/ciPR4++sgxWZue1jGt1aqOl246kbm3Hdgja2Zmr3vZ7bLW6ul+1HSa943zuh9dWNZxuwuLOrZx8cQZWTsd6/1sO7HIlbG9smZmNvait8jai4++Stb2nNAx4Q987mOydmnxRN/P0jQxs025zE4QbZ633IBY8ePL+l7UinT/Gtur41ZvKzh9Pe+PyQfn52VtZFjHv3ac559OU9eKBd1P2qmznDP2FLv6GFsrun+FeT32Jjn/Ge6Ccy9YffQRWauW9X18szysa5WqrHWcMduLAa9O6eu70tXPRZvbRMOGkfOqgUX93BSWdWzuhnN/GdoYHDfcjYmwBQAAAPAcYJIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADJ1VRG2aRhaGvbPS8pO/Fchr+cxhZKutTd13GgU+dFZo7URWXvxi3VUXaWgY9UKBR3xls/rWuxEb1qoY8xKRX1phod1ZGqxpOM808S/3IUB13bLI8cek7VGU0f8Wawj3jodvVwxp48xDEuylgb6+JNQt5uNlo6FMzPbbOprlc/p69914v96Hb3Obqe//Xe3afc7xez4qJUGRFsHXd0eVi5clLX7Hzgua/c+pNvtrj06XtLM7Nte91pZ2zM9KmvtVR33nMs7+bZOjGTeiYPcNzcuaxUn0rlU1P19pKjHdKvp/TQzi2K9P5stfY1bse67jz5xUtZWO5dk7fZDOsK3PqPP6YnzOkLz0VM6Mvj+p3RbNDPbLI3J2tSIPuc379KxwS977bfL2r2f/0Tfz+K4Z5vrS3KZneCN80M2XOyPK720omNKv3xC98tPnBwc02lmVjmkoz+rw/peZGZWy+lrGm3q8T8O9FjfcO4bZSeyO845nykHupY4zwUrDR2Zmrb1va/Y0MdgZhat6UjV9MnTslZ1PjfvVvVz4YM9/bx5cknfe8rO410x0c8UhbK+TkGkx0Ezs/aajg1upDpuN+88N8YFvc3942OD92ObqN0t/CUDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATF1VhG03GhxJttnQ0XBhTUe4tdY2ZS3q6ajDakXHdJmZ5ZwoyLVlHVXXcSJs1+s6jsyLbEw7OsatkNexYYWwP55vSzPWcWvmpIp1W85yZlYt6eawuHhe1jppWddyTkytE/2bKzvH39QH2evq6LtSUW9vve1H2C4ur8paanpfLdXXOHBiCisDrkVON88d5aEH7rHCgEjWdPmUXGZ0UkeR3vOwjhQ95kSfvvoNd8mamdl//W//Rdb+xl2vkbXxsr5QZWfsyhecsbKtx9jpyRlZS0o6fnN1QEzylQi8KEwzi5zProKCHiuOnzora7/2735N1pYu6kjHV7xSX6e3f9//V9ZmZnV7G+rpsWKu58dPPrymMy+TUN8rLp7WfePGfbtk7dDRm/t+1ou69uQj98hldoIbdudtpNQ/7v5wdZ9cZr50Ttb+/DEdxfpnJ/U97MX752TNzKz+5AlZW3P6Sc6Jvl/rOmNBVY8vcarvU1Gij/FSqvdlqaojg9t53Z5rgf/oOTSqjyNxYuFteUOWSs5YeNa5/y/HejyfLehY2OqQPje1Ib0vacuP913q6n3N55z49BVde1Gqn42GNwe3jRwRtgAAAACeC0wyAAAAAGSKSQYAAACATDHJAAAAAJApJhkAAAAAMsUkAwAAAECmrirCdnlt3Qr5/hi0uZlJuYwXb9tLdFTXxOSEXueGXqeZWa+n6x0n4jRxIkKPHddRdGGgI96KTtzjvgM6/i4cLslau6Gjw2Ln+HpO9JmZWcnZ17VVHf37+Dkdr3hweresTdRGZS0/MSJrjYaO21vt6f3MF3Vz39wmNm7VqSepE9npdLFCoKP4Gs3+eNFudGWRcde7pfWW5XP948ixwiW5TO7isqydPq/jlV971+tl7Wd/7p/JmpnZ//Wb/0HW/viP/lDWXrBHj4eFoo6RHKrpNh/H+tpPjOqxcnpCx5vmB8QIbyk6cc/hNvGT9Vi3625e95Xf+r8/KGuPHHtQ1koFva+//4f/j6ztPXqLrN1y4xFZq5R0DO9I6sRrmtmcTrW0nnNuGrGOxk27Oop4/57+SNfuNUYXX0863aZ1gv6+NFHW5+lVR6Zkbamh7+H3nNP3lEcv6GhzM7MbnWjUrnM/ShPdFjbb+vqlHd0XCmVve87Dj1Pz+sJmqu+ZG07sspnZ5AtfIGs5fanswT/5lKzNO+dt77iOrLaOfqYq5/XOrEf62jeW9TPqrBMLbGY2N6XvL8XQed5Y0e14/6aOcJ4fGxv48+Y2cd1b+EsGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNtzi4uWC/tjqwoFHcvoxabOz8/K2qAIzy0b9e0ibHXkWi7U+9rs6aiyR48/JWt5Z50LZ3S85tTEuKyNjo7J2hNPHJe11PSxf9fbXiVrZmalVEdojo/VZK2yoSNll9fWZC3p6vg3r01t1Kuy1ug0ZK3ptMWwqCODzczakd7XIKe7UZLo5VbrOlJuqlbp+1mcXllk3PVubt8hKxQKfT+PbVMuE0U6DrE4pCP/ds/vkbU0cGIbzWx+bq+s/Z+P/C9Z21zU/bpa0e2sVOm/5n9FX/tSvv9cbhl24hCrFd2Pik4sbLno7adZWtbHeKmlr/HDjz4ia296012ydtuLb5O1//ifdCzu5//yblk7NDsma8WqHpuWFhdlzczs/icel7XCkD6vu0b0/sQtHW9cKfZ/jpg4kes7RZDLWzAgBjvo6eeG3WM6bvXOgzpOfaOrx56Ta/6zSDOn++3M/Lys5Yq6b7ad55v2pu5feScCvVjQbU+fGbPeBR07PuJEWXe2eQ3BinO/HRvX4+tYoD83L7T1NvcMDcla0fksPhjSY11Q0OsM6/pZc1deX3szMyel2cKOvsZNp22M5vS5ObxvcL+pd/247sv7dEW/BQAAAABXiEkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMjUVUXY9tLU0gHpacvrOopzpKpj47wo2lzeiQU1HSFoZtZo6fWGzrQqTXTEaa2it3lxRW/vvgdPydpQRce/ddo6FtZMx7sVy3o/H31C74uZ2a7qlKzVhnRM5uysXm75lI50DPI6i+3iJX1u9u6dlLU40evsONF/zYaOdzMz6znrjb12M6IjRLuJ3p/GgHjfqLfzoyfNzHoWWzDg843YOR/Fko71G9LJy+4Yc+GibmNmZksrq7J2dnFZ1tKe7rvlko6KjJyISS9st1TQY+VQSffbXF6PFZWyHrfLZT9iMXFiO09fuqAXdCKa3/nd3y1rd955p6ydOXNW1n7/D/9I1u69f7+sxW0dP7l6Qd8Lzcy6y+dkLR/rmPBmry5rT62ekbVqqT+KuBd595adIU0DSwe0lzRxYloTHW9784TuQ5d26zG80dHrNDPrtXT87dTktKyVh3Vw7JozTkZdfW17Tq2T0/sZBnqcGHGep/QIYtbd8PuJtfX+pIsXZW2vE/VdyOnI1VpL789MTo/Zq06Ecammo3aTSJ+4XnNN1szMNjp6m06CrSVOvP/um2dk7eC+we10w31G/Sv8JQMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMXVWE7djEhOVz/XFmIyNDcpmyE6+4sqFjQysVHZMYdZ2cLjPr9nQ9X9DzquKAuL/L64x1XNfFFX0c7Z7e3kRtTNb2HtKxsFGko9g2Ntdk7eRZP7KzOK3jLsNUb3O4qs9bMKNj3EYqOnu0vrYhaydPnZS1w0f2yVrXicjsxjoyz8y81GA3/nbfhD7GSlmft06rPyYzTv12v1Msr69YfkBEddTT1yDvZE+nTn+/94GHZO2W214qa08v+6CsRc7nM928jjzsRjoO8vz5JVlrd/S5KTpx3wUn7Vv3BrNCUY8FBWdMNzOLU91Z6m0d9zwxtUvWpiZ1bPXmhh4rZnfPytrKqh4P//RPPyZr7bqOglxe1lGzZmaNQLebfKUkazln7BrfpaNQZ3b1H3/c02P5TpEEoSUDzmXsxds70dKjTpz6S+adiPbNFb09M+teOC9rUUO3o+KQHkPaThuKUl0LE338sROfHcT63PScfekWvBHGb4OBM6bHOX3ftNCJmnfafepE5pZjPRamkY6zXiyvyVrkPGsmehgwM7OC8zqBZlPvT9EZl6f36XGynB+8r12nzzwTf8kAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU1cVYVtvtiyX65+XJE402tyuGVkrOjG1zY6O4hqq6lhQM7Mg78Sx5VJZKxR1xFfgRNE2W3p7xUpZ1oYnh2UtCnXcWi+va+UxfU6TvI4+MzPbrDdl7cZD+/X+LOrYxl5DR1au13X834033ChrZ888IWuRE30XOM29vqGP3cwscebjw1V9zr1430ZDbzNXrfXvgxNdvJPEQWJB0N/XAieasN7U56pV1+1v8dKyrP36//WbsmZmdur4Kb0/Toz28XM6GjVN9PgTx3qdUeyMTXFH1nJOuw2cENvAGdPSYJv4Sa+Y6uOvDOnjWF7W17FU1O1mY13H23Y6+jhOnjwra168ZuREXZuZpWU9VugzY1Ys6GMcKun7SLPRv69eO9spipWqFUv943nOOb/dNT1OeBGuc8499ZZ1P/r80bULsra4cFrWNlq63dYT3cjaTtR3wRl7ek48epjq+2Yj0L296cQu57f5fDvp6GNMnDjvwImwNef4284zY+JE3za8dZb0eGah3l654GfYJrHzbJzobd6wq/+ZYst4UR9Hc3lt8M+d8fOZ+EsGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNtKtWL5fK7v53FPR2p1Ih1vmy/0r2tLwYnsy+X0ck/Tc6fQSXHNF7bJHxQ6ToRvMOB8bamO6mPc3NyUtUqlImuXLulY2HxeR5iZmY1X9HmrjunY4OGyjqndNT0qa0vpqt5eVV+omZlJWdvc0NF/Tuqoecl3ZmYjo2OyVhvR12NjfU3WlpaWZC0N+2Mpe0505k4yPjFuhcKg66v7SqvekLXOkI7wDAPdptdW12TNzGxyWsdvj05My1rPiTVMUj1W9iIdPxg7MYqRE7+ZRNcWmdtxIsQTJ4bWzMxSPY6Gzti85vTdz37us7L2hje8QdYefuRRWfOSXLvONcw57TRx2puZH0Ucd/R9xLp6f86cOiNruVL/mJ8mz4NxJMiZhf3XIQj0fSOvh2lrh/rcF5x4z327dbytmdmJs7ofdTt6TIsTvdya87y1FOhHuprz3BQ4fTpwYmrXnUemReeG643LZmY5J/7W46214PTbC84z3Lrp46g7x7/HeagYc8bs3Ip+9jMz25XXr0V46fysrB2e1x2g2tLxzh0RmdvtEmELAAAA4DnAJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMXdV7MsqV4sD3ZISBft9Dq6uz30uJzi2ulPQ6A/PzeYvO+zcsp7OLR0YnZK29sS5r3bzOrc6XdJByq9uWtVxOH78Tp2/dls67Pt/W72UwM5vYs0dv8/xFWasEepvlmr4W06P6PQRLy6dlbWJUv7PDexFKvadP3NHdc3qdZpak+jiaTZ2x3Wzo2oTz7o1oQBPv9a4tO/x6E1tiofX3iyTRfSXvjAelks6qz+f1EDc+PiVrZmbmvJckcd6jEDp59L1uU69T5JGbmcXO+xW88+a90qI3qJF9Tb3h5KZ3nAHIzKLIOQ7nnHrr/egf/7GsPfTII7L2lXu+KmuBM1bEpvtazzmpsfOOEDOztOdcx1hfD++OFw54X8SWcto//qTb7OOOkIZmSf9npJ2W7l/euxcC550GaVeP4cNDQ7JmZjY1ovvCyiV9T91c1LX1nP5s+HPO+x7GnbFgxHm/yJDznowo1Cvd6Ola23n3hJk5vc8sF+rjLzpjb9Vfq6zkA91fqs7xJ8742o31vlS2OTejw85oEOl3DdVX9XFsjOjrH/QGt6lN510fz8RfMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMjUVUXYFnOh5QfEp1WrOkIyjnXMVc6J6so5UbNxrGPazMx6PR0blzrxb5ubOsastaGjwbzjKJf1Ke46EWdRS9ea6zrqsZivyFptYkzWnl64pPen2ZK1XFHHuBWd6NG0oM9NbUQfR2lAjPKWsYlpvb2NFVkLQj+Orb3ZkLVW07n+Tt8InGjAQdmjkdNedpIgyFkQ9F/DQkH3zcAZD8yJAywUdDSfOZGOZmapc31KTlSiOcsVnRE3sLKseXGzsRNh62XYelG7k1M6znu7duhFpPpRvLofNRo6mnTxwgVZO3DgoKxtOvHSzZYe77yG48XbmvkRt6lzHb1rFTqRnuGAaNYkSay1uSqX2QniJLV4QIx06kRLB869v5h37lMt53ljmzFkZkiv96sPPiRrywuXZK0X6EHkkhPTuuE8F1Wdfll1ht6Sc07Toj52r82a+ffGfN6Jnnb614bz3NhzorW98azoHYYzTibOeQvzfqNKTB/HWn1N1nKp3p9SWJO1IBnc3upE2AIAAAB4LjDJAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZuqoI22qhZIVCf5Re3olN82Yx5bKObKzX67KW8+IjzaxY0lGslSEdKeou5xxIa31N1nbN7JO1thN9Ozakz01h2onbc9IsI9PRt2ZmvVhHnFWGh/T+VPX+OE3DIiembmp6WNaKIlLNzCznxNuVSvqcpql/bqpVvT8V7/idttpyYjIH1aIrjIy73qVpztK0/7ykiW4PgdOQvCTgxIkFdeNtzcycqGQvYjH0dshZZ86JdSw40ZxRpCMNvQhxr296UaC5wD9v3jjiDd0F5/grtTFZ27NP97/EOY5WV58bL6bXa1NeTKqZWepE3Hrr9e553jXudPrHtV6vZ+fPnJLL7ARhvmDhgAj0gpP+GXi1nPMo5JzfuKGfU8zMdtf088ZkQa+30Nb3hhFnnGwHTjSqU+vlddtrOO2y5aWtOpGxuZ4f0+qN96H3igKnf6WB02+dfSkMiFu/XHPaTcU538POMDEU+Pd5p9mYOc+UnZaO4feacTUc3Ia7kfOw+Qz8JQMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMXVWEbcFSKwyICAudyMKiE/HlxpQ5cYZe1J+ZWdGJpuz1vGhCXSs7+zNa0/GmoZONVi7qeLvEiVesDuvloo6Od2u3mnpnzKzTc7ZZ1NexUNTRv42m3ma5NiJrra6+Fi3nGAupvva5UEfRhTkdb2tmFjvT8WZLt8e1tVVZ89pisdgfyxl4GYw7SNSOLR1wQr1YWC8Z1Is+dWNB8/7wFzhxs6k5UaROLXAjJnXbLVR0Lc3pqMjSNpGqmr4WXkykmd+uo67uu4mTv+2ts9nVy3nxru2ePm9eW7Scc268yGAzS532OKjPb8lv01aVarX/XtFzIo93ijCfs3DAOcmlTnv38t3dCFvd9/LeDd7MhgPd3l/7wjlZW2/q5e49vSRrSx3dT9pOnHPH6e+Jc24S53Pq2NleuM29zOt+YXht98GcM/bmnVVWQn381VC3jVpeH0Qt1G1xcpuuXnVOTsGcZwrnvKXOM3xbxCm3e0TYAgAAAHgOMMkAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJm6qly8ciFvxUL/Il5MYJroWi6n479GRnS86XYRtl78oBcpmjoRtqOViqwNO/GuaaJjMFsdfW4CJ/4tiXSEXW1Ix+lukzxpXvhio9uRtUKkr2OrpZfrhYOj0czMltY3Za2+vCFrY2NTsrbc0Ne+XPHn22mqr/Hqio7p3XQifCtOmxpU6zkRwztJmgaWpoP6qO63sXfsga6VSjpeOdomyjOOdb1Q1G3eG5/yppeLIz3+9Jy+60XKenG6oRO/6Y2hgRMZbGZWKOkxL1fQMa3eNr17jHe+IyemNnTG+8TZXs+p5Qa262es14ni9a7jdrHByqAo+O2u345QLJsN7IP6/AbeOXQigntOG0q2eYTyokF36yR6e/tte2RtV0G39+MX9L3xQkMfx2pPt9u28wzTcU5pL3DauhMna2YW5pwxxKl5va/gPFPlnUfKISfCt+QcRynQKx3J6TFk3Im+fXp/9DbLA57PtziJ7O69sCnury0ibAEAAAA8F5hkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZOqK0qW2ki2iaPC3zONYf8vcy8RInDQVL6Rju3SpQYkaWyInpcZLwuqKYzcz6zqpKGGoz0A31fvppUsFzsnpdHVKQNc532Zm5iRhhE72VKerl/POW3KNy3nX0DtGb7lc5Ke3DE5DepqX+uT1DW+5QbWtn11r0sxzbWu/VVqLm2iUOv028BKUnD62TcpOfI0fwSSpNx461y7Rx586Y57XHrzj99KlzElN8a7T03VdS7xxzVnQS3ty06WchLDIGe+97blJV9ukS6XfgHSp2FnnoDa+1f924jiytc+b7cHXNXbuKX66lK71OnqdcXebxD9n3EqcJKy6s14v1afj9K+uU/Nufz3nvHmpd95y27W80FvWG0OcdXrX32sakTtmXVvNu07tbUKbCrGzs87zpvO4abGzr6lob82v7cd240iQXsFIc/bsWZufn9/u1wB8E5w5c8b27t37XO/GVWMcAa4fO3EcYQwBri/bjSNXNMlIksQWFhasVqtt+ykWgG+MNE1tc3PT5ubm3E+or1eMI8BzbyePI4whwPXhSseRK5pkAAAAAMCV2lkfYwAAAAC47jHJAAAAAJApJhkAAAAAMsUkAwDwDfeLv/iL9uIXv9j9nfe85z32zne+8/L/f/3rX2/ve9/7vqH7BWDnYBzZWZhk7DDvec97LAgCC4LACoWC7dq1y77927/dfud3fmfb94cA2Fk+//nPWy6Xs7e97W1XveyV3IyvN7/xG79hH/rQh57r3QCeVxhH8FxhkrEDveUtb7Hz58/byZMn7e6777Y3vOEN9hM/8RP29re/3XrOi5m+XlGkX2wFIHsf+MAH7Md+7MfsL//yL21hYeG53p1vuNHRURsbG3uudwN4XmEcwXOFScYOVCqVbHZ21vbs2WO33367/ezP/qx95CMfsbvvvvvy7H1tbc3+7t/9uzY9PW0jIyP2xje+0e6///5nrecjH/mI3X777VYul+3QoUP2S7/0S8+apARBYL/1W79l3/Vd32VDQ0P2L//lv/xmHibwLa1er9vv/d7v2Y/8yI/Y2972tmd9MvehD32o7yb6B3/wB5ffHfChD33IfumXfsnuv//+y3/53Fr+9OnT9o53vMOGh4dtZGTEvv/7v98uXLhweT1bn1z+zu/8ju3bt8+Gh4ftR3/0Ry2OY/vlX/5lm52dtZmZmb7xYLv1bvnt3/5tm5+ft2q1at///d9v6+vrl2t//Z85/HWdTsf+8T/+x7Znzx4bGhqyV7ziFfYXf/EXV3ZCgW9BjCP9GEe+eZhkPE+88Y1vtNtuu83+9//+32Zm9n3f93128eJFu/vuu+2ee+6x22+/3e666y5bWVkxM7NPf/rT9u53v9t+4id+wh555BH77d/+bfvQhz7U1+F/8Rd/0b77u7/bHnzwQfvhH/7hb/pxAd+q/uf//J/2ghe8wI4ePWp/+2//bfud3/kdu9LXGr3rXe+yf/SP/pG98IUvtPPnz9v58+ftXe96lyVJYu94xztsZWXFPvWpT9knPvEJe+qpp+xd73rXs5Z/8skn7e6777aPf/zj9ru/+7v2gQ98wN72trfZ2bNn7VOf+pT923/7b+3nfu7n7Itf/KKZ2RWv9/jx4/Y//+f/tD/6oz+yj3/843bvvffaj/7oj17xOfkH/+Af2Oc//3n7H//jf9gDDzxg3/d932dvectb7IknnrjidQDfShhH+jGOfBOl2FF+6Id+KH3HO94xsPaud70rvemmm9JPf/rT6cjISNput59VP3z4cPrbv/3baZqm6V133ZX+q3/1r55V/y//5b+ku3fvvvz/zSx93/vel+0BALgid955Z/rrv/7raZqmaRRF6dTUVPrJT34yTdM0/eAHP5iOjo4+6/d///d/P33mkP4Lv/AL6W233fas3/nTP/3TNJfLpadPn778s4cffjg1s/RLX/rS5eWq1Wq6sbFx+Xfe/OY3pwcOHEjjOL78s6NHj6b/+l//66taby6XS8+ePXv5d+6+++40DMP0/PnzaZr2j2+ve93r0p/4iZ9I0zRNT506leZyufTcuXPPOqa77ror/af/9J8OPonAtzjGEcaR51L+OZzfIGNpmloQBHb//fdbvV63ycnJZ9VbrZY9+eSTZmZ2//3322c/+9ln/eUijmNrt9vWbDatWq2amdnLXvayb94BADAzs8cee8y+9KUv2e///u+bmVk+n7d3vetd9oEPfMBe//rXX/N6H330UZufn7f5+fnLP7v55pttbGzMHn30UXv5y19uZmYHDhywWq12+Xd27dpluVzOwjB81s8uXrx4Vevdt2+f7dmz5/LvvOpVr7IkSeyxxx6z2dlZd98ffPBBi+PYjhw58qyfdzqdvrEOAOPIIIwj31xMMp5HHn30UTt48KDV63XbvXv3wH9juPXvL+v1uv3SL/2Sfc/3fE/f75TL5cv/e2ho6Bu1uwCED3zgA9br9Wxubu7yz9I0tVKpZL/5m79pYRj2/ZOHLIMZCoXCs/7/VprdX//ZNzPRrl6vWy6Xs3vuucdyudyzasPDw9+0/QB2CsaRfowj31xMMp4n/vzP/9wefPBB+4f/8B/a3r17bXFx0fL5vB04cGDg799+++322GOP2Q033PDN3VEArl6vZx/+8IftV3/1V+07vuM7nlV75zvfab/7u79r+/fvt83NTWs0Gpc/CLjvvvue9bvFYtHiOH7Wz2666SY7c+aMnTlz5vKnhY888oitra3ZzTfffM37fKXrPX36tC0sLFx+6PnCF75gYRja0aNHt93GS17yEovj2C5evGjf9m3fds37CnwrYBwZjHHkm4tJxg7U6XRscXHR4ji2Cxcu2Mc//nH71//6X9vb3/52e/e7321hGNqrXvUqe+c732m//Mu/bEeOHLGFhQX74z/+Y/vu7/5ue9nLXmbvf//77e1vf7vt27fP/ubf/JsWhqHdf//99tBDD9m/+Bf/4rk+ROBb1kc/+lFbXV219773vTY6Ovqs2vd+7/faBz7wAfuTP/kTq1ar9rM/+7P24z/+4/bFL36xLxf+wIEDduLECbvvvvts7969VqvV7E1vepPdcsst9oM/+IP267/+69br9exHf/RH7XWve93X9U8jr3S95XLZfuiHfsh+5Vd+xTY2NuzHf/zH7fu///u3/ScOZmZHjhyxH/zBH7R3v/vd9qu/+qv2kpe8xC5dumR/9md/Zrfeeus1vQMAeL5iHBmMceSbi3SpHejjH/+47d692w4cOGBvectb7JOf/KT9+3//7+0jH/mI5XI5C4LAPvaxj9lrX/ta+zt/5+/YkSNH7G/9rb9lp06dsl27dpmZ2Zvf/Gb76Ec/an/6p39qL3/5y+2Vr3yl/dqv/Zrt37//OT464FvbBz7wAXvTm97U92Bg9vTDwVe+8hU7e/as/df/+l/tYx/7mN1yyy32u7/7u/aLv/iLfb/7lre8xd7whjfY9PS0/e7v/q4FQWAf+chHbHx83F772tfam970Jjt06JD93u/93te1z1e63htuuMG+53u+x9761rfad3zHd9itt95q/+E//Icr3s4HP/hBe/e7323/6B/9Izt69Ki9853vtC9/+cu2b9++r2v/gecbxhGNceSbJ0j/+j/IAwAAAICvA3/JAAAAAJApJhkAAAAAMsUkAwAAAECmmGQAAAAAyBSTDAAAAACZYpIBAAAAIFNMMgAAAABkikkGAAAAgEwxyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJApJhkAAAAAMpW/kl9KksQWFhasVqtZEATf6H0CMECapra5uWlzc3MWhjvv8wHGEeC5t5PHEcYQ4PpwpePIFU0yFhYWbH5+PrOdA3Dtzpw5Y3v37n2ud+OqMY4A14+dOI4whgDXl+3GkSuaZNRqNTMz+42732qVoUJf/Yt/eVEuO1w6ImvVak3WCoHetaFq/z480+TIrKyNVffo2siIrC0un5W1k0sPylptriFrE7t1rVBqyVqrsS5r5bI+N7lgTNbMzJK4J2txXJe1sZE5WSsVK3p/TK9zY7MraysXc7LWaYzKWrMzJGuppbJmZra2uihrrZbe1826vlapxc72+s9N1Int9//dVy/3x51ma79n9x8a+MlHmDptt6Kv+Z4bdX/3Puw8feK8LppZkugxaHhk2KmVda2oP/HZNbtL1tbruq+srK/J2vjEpKxFa3qMqV9ckbWxmj52M7Nd83o8aPTasraxordZrzdlLefcxqKO7mMbmxuyVhnT1zByxskoimTNzCxO9f6kia4V8/oYK2W9r91u/9gUx7Edu+fRHTmObO3zz/y3z1mp2t8OY+ccxqke470niqIziAS5orOkWTfRy9Yj3Rdy3h+Y2rov1ColXRvWtZ5u0laP9NgbOucmcu5vSer/FSrYpn69SJ02lVriLegs5z+LmF3judlutXJzg7fXadbt195957bjyBVNMrb+LFkZKlh1uL87Fst6NaWy7oRlp0N4k4zKNpOM6pB+sB2qVnVtWD+EVtt6neWmPo7KkL7pVGu6VijpXh+E+tz4kwz/vCWxbrxx7Ez6avoal0r63ORNP5zHTo9oN/W+hKb3Jc3rfdmuY7c7er2Js2wn1uc8dQaLQksf4079ZwJb+x2GoYVh/40rTJ2bWU7X8gXvXOn98db59MK6nnMe+rz9yRf0OotF3cYKRd2OvO15y6UFPcbkneMr5P1xxDuObqhvvPmCc4zO/niTjNQZ03LO9feubxLo/p6kzoOFmbnPHU5bzeW9fXVqia7txHFka59L1WErD/U/3LiTjESffHeS4fxTkO0mGaEzyYi6Tpv2JhnO/pSr3rOInox6k4zeNU4yckwyvAVlKXFqT/vmTjK2Gye2q++sf5AJAAAA4LrHJAMAAABApphkAAAAAMjUFX0nY0uu9PR/f93QlP5S4gP3fE7W5mdvl7Wa872Kdtf/t9StTf2Pz1pj+t+P9QL9harxOX2qbpzXtVb5gqxtJmuylmw433OInS8wl/SxR7E+PjOzfE5/oXNiZErWqkVnmw39paCNxm5Z21zWX8o8/fgpWcuVnH8HWdDfgTl7Tn+x28ysNqyvR31T/9vTXs/7N7vOv8sccBjJtX5x6zqTRqmlYf/BeP+euhXra7d4flXWZqZ0Xynn/c9YwkCPQQXn37p3Vp1xZFp/J2zvLv0l7aGKHmOaG/oL09bRY/NNN+kQjNk7XyBrw8536czMSs4XTDuJ/h5Wp6MTSjbWNmXN+/7epYVLsnbilB4rihM6BCRX1tc+DvTxmZlVnFCAckmPFbWybscF7/sjAwaNTrtrD3/pIbnMTpDmCpbm+r9JkXj/Xt3p7q2O/lJC2/leT3GbQTkI9bJ557uVQeJ8ScI5EO+7Do2280XzQLe9INTfWPGiS0PvWmzz1aXgWr938A3gXWHvDpJzrn3ofF8linTNzCza5twp1/w1F/Wdi+DK/kbBXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2J6/tGLlZv8icwfH5TK5nI4wnRg+5GxNR1aeO/GUs5zZiXPnZW3PnI6XbKR6X8fzOiazN3JM1sLhZVnrRDoabnNNR9hN5HUMZtGJkx0Z1RG1Zma1io6Q7ET6enR7Om7Wejpvbf3CtKytPqWb5uNfuU/Whub1edtzw4yslYf0tTAz29jUx9hpO3GDgV7v0rKO1+xG/XGDUcePttspSsW8hWF/DGjqREXGsRMk2NORojPjOnq5veJHOrfq+rqWczretlrV/fOmozfI2o1HDsjaet2JcC07nxUNiArecvMtensHD8zJWrfT0NszszTU523AZb8sX9B9Jek6kY8NHRvbbczK2ivbN8laUNBRs2HVibAt6nHy6WWdWsGJSnXGkVBFTJpZmvZf/2a9bb/5fr0fO0HUSyw34N6SOuOEl+A5aDx65raUJNnmensBqDmn38ZOvHJRR0T3Br1j4Guake6XlYITRZvX+5K6MbXOcgPa5bN5V8upXWvMu9OHEuc4Ame50Il49Y4/3eYgtj1117DNa1kujb2Y5b/CXzIAAAAAZIpJBgAAAIBMMckAAAAAkCkmGQAAAAAyxSQDAAAAQKaYZAAAAADI1FVF2B4/XrdipT/q7cAhHUV68Og+WXvqieOy1mjWZW2o5uQAmtlma13WHnrsQVkbnrtR1iZrOiaxF+qIs7NP6QhbS/VxjBd1hGRqTrRmUV+LidFdel/MrL5elLVjj+ptjg/pmMjaiJ7HRpM6NrBxTq9z8cKYrB3cq9dZHdb70kv8NtVt6/aYL+r1rq7o6NFmoz+mdksw4DDi50eCrVVH85bL9R9gPtHnsRbrSNFKSdcC3W2tmtfLmZm12zq2uFlfkrW0qo/j4oLe5r2xjtRtdzuyNjmjo5l379X9aPecjvetjOn91KPE00rOL5SLun968aNRQx+/VfQGO07fTDt63A5j59ZY0rGVlZlRvZyZ9Sr6GDtOY00DvZwXsZmkA2rh8+CzxTQdGK15rTGdniD4OqJYB4xzV7KsF40adVqyVjTdhorOeOcHuGuRefG2mnN42/uGrfjqeX0v8q6vt850u/6pt+nx2pRHHsUVru95MNoAAAAAuJ4wyQAAAACQKSYZAAAAADLFJAMAAABApphkAAAAAMgUkwwAAAAAmbqqCNuzZ2MrlPp/npqOVNuYPCNr3VBHzcb5SNbGxidkzczsxqMHZe3CRb3NRqQjRR94WEfR9kKdLTo2pWNxLdXxpoWS3pfxCX38w1UdS7m54UeOLV3QMZFJVzeV8khN1ja647L2YPuQrHUmJmUtnDkla9Wyvk6rayuydn5BXwszs15HR/hGHX2t6g0dg9rreVHE/R0tyX1z4/m+Ufa9YMYKxf72VGrraL7epo4DPHduTdYee0C3hzD1h7/Oho6UDXp6zAudaNQTX9Hjz+kB52RLb1AU6ddM7dIRtqtOhO1QcquszYzcJGuzu/U6zcyqJX2tSk4Ua3dTn9N6V/eV7oaO7ayfvCRrGxdXnX3Rfbpl+t40dWRe1szMwvGKrJVnhmUtGNNRqEGox4VC2L9c4XkQYRtZauGAcM3gGmNDvVroxclGul2a2cCo7svbdK5DbPqZIudcvmpB7+uQbnrWa+qxrhPqePeO6ePzbHcnS53xzq5xm99sXkSxl8L7jYhh/vqoq0WELQAAAIDnAJMMAAAAAJlikgEAAAAgU0wyAAAAAGSKSQYAAACATDHJAAAAAJCpq4qwjTsFCwbEh61d1BGCUVPHBJaGdFTX+KyOaU1LfmzczA06CnAjqctavaWPo2J6f5aXddxhrTgqa3N7x2Qtsouytp7o7TVWlmStnNP7YmZW1wmSVhsZkF38Nb2ivsYXGzpe82O/r893ki7I2uGiXmcu1fF2Sws6Trbb9mPjcnkd19aOdKRl6sQfDtf09QjSAcuFfrvfKd709ldZpVru+3njpG7zn7/7C7KW6zRkrbmhoyDj2P+MpeIEDY5WC7I2VNDbnMzpOMixqtM/805sY6Rr4Tnd5u/76Gdl7dR9j8ja67/jTr0vZvaiFxyQtaGC3tfium7fwZI+p8undTR1+9h5WWss6njbdkcPhgsba7J26gkd2W5mlp/U17i6T8d93/ztt8haoarH5ijujwKNnIjlnSINnv7vr3PSfC3nRG4OWtdfrVOPE95yZmapM4bkC/rxK3T2NZfT64xi3YfadR3TXl/Q/WTqyIv09pzPqXtOM0sS/37rndcgca6js9prjTD2XGsU7dcVU/sNSbh1Vqr21Y0Z/iv8JQMAAABApphkAAAAAMgUkwwAAAAAmWKSAQAAACBTTDIAAAAAZIpJBgAAAIBMMckAAAAAkKmrek9GMchbIehfJGrp9zaMz87K2rkLF2Rto31O1tLwcVkzM7vtRUdk7VVv1vszVKzJWtTUtccf15nqG6s6i71S0fnmcVHnwp/dOC1rkzX9zoa58aKsmZnVJiqyVnTmo42ezlh+8uwpWXvqM+uy1t18UtaCeb1c86J+L8Du/fodBZUx/9xYqNt4mNPLVp33KXSd97IUwgH7Gupru5PcfMucDdX629rxVkcus77alLXJqu6bPecdJkub+v0KZma7nTZxw5jeZt503x00fm4ZH+l/d8iWYmVI1mKnb5bLuk8PDel0+PWL+tw89tFPypqZ2djirbI2Mz4ia722896crt7XQkuPPyUnj7+5pt8pZE4EfLyu2+Lakn4XgZlZ9ZJ+p0u0ppftvOSQrOUO6DYVD2j+A16dseMsnDo7sE/kAn1wBeddM0FRj9NBTvevUsG/b4SJMxZ09HqTvL6m5ZzzVoee3l4v1ftamj0ga6tNPS43nHeI5J37Yhr4L3tInHcwBM54F4bO5+beuznc91Y47+Vwa87mnNp2Au9lMN4bP1LnfS/OHiXB4Hto7O7HX+EvGQAAAAAyxSQDAAAAQKaYZAAAAADIFJMMAAAAAJlikgEAAAAgU0wyAAAAAGTqqiJs62sNyxf7Y+BGpnT81fLGeVkrD+sIrHqjJ2uRE9NmZnbskROydv6cjn+t1XSE5K5d87I2c0BHtTVP6cjCM5d0TGulpiPcJqd1DOT4iBO1Gp6VNTOzfNGJ0AxHZa3XnZK1JHJizpJVWbrpFh1T+4KDular6ri98Wl9TptNHRFqZtbt6mu8uayjmOOu3malqCN1LR7Qp6KvJ/ju+jEyUrDhkf7IyKWlZblMIdTXZzin2+1qouOlLdV9xcysmOq2u6+m96dS0lGZXedjnU5X7+umE5tarOg43bSgj6Ea6PM2M6X7dDHvt8PmmUVZO39RR3r3Yh1hG4Y6itdSfb7zJX38XmR3Z0OPI9WSPm8rdT02mZk1L+ho4NEBsc5bhgMn7jzU98ruwGFE//5Ocf/ZRcuVBoyf///27jzI0ro+F/jzvu9Z+5zTfbp7ept9mBmGGXDAYRNcAkQCemOCsURLqwxJSKpSpYm3LCoaQzYqlYRsVZY3VSlNheQm915RK4RcJdfSCEFUlGVQcRyYYQZm6Z5eT/fZ3/X+gTOC5zzf6SEvS5vnk6Iq9NPve971957faXxOwt8bWPWmWauK1agFzWR49e3z6+X3SpZftugYj83xIf783zrCs8kCf7tXHuDjWbvDx0kn5juxtMLvhbZvj71RyK9Rz6gNzuX4fWLVtHpGZXC3w8cCx7g2XIdnXZ+Pdda+A0Amy6+5olFZ7hr16daIHpJbo9sxnq0vfN1V/ZaIiIiIiMgqaZIhIiIiIiKp0iRDRERERERSpUmGiIiIiIikSpMMERERERFJlSYZIiIiIiKSqnOqsHViB07cW8vlZowq2naNZhMT4zTzwCtTT54MaAYAKwmvGFxZ4tVhmQKvV1xo8myoMkyzQplXig2ObqRZMc9PzcTwlLGc0YsH+7gFAa//CwJeL5pk+Vx1ZWmMZoO8bQ/XXD9KszxmaTY1WaZZzjg2T32XV80CwOISrxDtrPAqt8SoWx5ax7c16rdcbG/jWlHM5VDsUzXoGMeqvlSjmWtU2GYcfs0nrJvvh8KQn58g4DWCpQF+nrIef816nddd54xqwkqZ73+2T+X4ac1mg2aI+PgzUrXrnjtdXvkYGe3jQde4x5q8+rVe58sNlHjd5XCZn9/ZFf6cKBR49XQS12kGAB2fX4/HnuPVv9uO8efP+Fb+HIni3nMRxWu/wtYZGIJT6HMdJryM06rp7BohvxKAyFwrAKMueCDmywYRv05KLV7/mpR5hWt1hN/TUxX+Hs6r8vtkfpmPWYdn+X15aIEvBwCOZ72P4et1jMrgvMfH7Kxr1I53jQpfo2rYiMwK2yCw36dZVcwFs8KW72OS8GcWe4QEHfscnnndVf2WiIiIiIjIKmmSISIiIiIiqdIkQ0REREREUqVJhoiIiIiIpEqTDBERERERSZUmGSIiIiIikqpzqrBtNhrw+tSVek0+V6lk+UsELV5F5ho1ZcU8r0gEANfhlY6V4SrNIo/XzbV9XiHYOsXryLZtuJBmQ0Ve74rAqLdb5pVywyVer4isVcYHtKxKsgw/NrHHz/Ezh3ht3PAEr9vbdymvsC1iJ82CiNdydpq8VC4MTtEMAPw2r6bMe3w/iiWeWS19jttbKRcbNXNrShA+/8+PyRr1plnj85DqUIVmAzEfC46t2BV8XaPGtd7hG5vN8rErk+fXQxjw+3PjJl5TOjQ6QrP5BV49HRivFxpPhsCoXwSAfJbXxnbaRr1tmx+31gpfbmVxhWZJyCsdy2O8ejzoc32e1mjyislW17iIAQQhH9c783yMOfLUMZqtu2o9zTLZ3kGm38/WmsT3kTi9F2li1MI6Rt9obFbRWj2lVlHp82tmQodnhYRfR65RQTyzzOvUY2O5ozV+73Vjfr3UjHthucVfrxXZ1b8rxv3nGs8C6/xnXOs1+X5Yr+cYz2SjTRlI+BgZx/bb8sQ6dkYNfGJcU9bGsks86q6uClt/yRARERERkVRpkiEiIiIiIqnSJENERERERFKlSYaIiIiIiKRKkwwREREREUmVJhkiIiIiIpKqc6qwdXMOvFzvvKTd4fVfjWd5LV93ntetja/nlVqlIq+BBIDldo1mlQyvQhyZ4FVtc3NGFWnEK2WjLl9np8Fr4/JOiWauV6XZ4rxRn1my6xUX6vzYtBu8GhYZvj3HTvBLbGrjMs0KZV5LmenwCs12m1f4Jt0qzTZusGs5h4xq4JlneRVqqWxsj8tf0+nT/Ns17rO1ZGWxhjjovdaaC0t0meEBXlNbyPF70+/yYxZn7Puh5fDxaalr1HYP8trmrFF5OVjidavVIX4dVcq8DnG5xvdxYYXffx74mDY2ws/F2XQ6Rv24z8d83+dVkY1Gh2dNPm7l8/y4RS4/T/N1/kxbsvYPQCfg+9Hpc0+cdvLEPM3sa7z3mMbJ6qonX8uiMAT6Vs4bVZzGOY1jox7cqvd07c9pHaP+NnT4eisuv28LxkvOG+8pOgEfl9waX2nLuC8LnnFMjbGuZOwfAPgBz6OIj/dW1XkCvs7Y2g+rptaoITYb5xP+emb1LYD4bL/AGNebdd+w/Yise+YF9JcMERERERFJlSYZIiIiIiKSKk0yREREREQkVZpkiIiIiIhIqjTJEBERERGRVGmSISIiIiIiqTqnClsHEZw+9VlJh1eDjQ2uo5nX5lV6YZ3XrcV5e7P9Dq8YnJ/ndaNJ1qhcy/JK2bHx9TQbH+X7P1YdpxkCXn2b9Xj1YuDxysaV5hx/PQDHTx2h2czxUzRb5BHC7l6aVap8e2bmv0+zIYfXeQ7k9tBsfP35NFu/wa7ldMICzeq7efWoH/LzETm8brDV7a1PbTe7AL5Il1kr4iBE7PfWbgZ1fjxGyvz8LNd43fFcm9e0rtsyTDMAGC7xMWjm+AzNBjtTNMtn+DpHR6o0Kw/w6y/j8SrBwUG+3MnnePVrs/kS6z4BNKwazRbPYqNFemmFb2utzheME55lZngtbK7Cx/tGzJ9by6FdD9s1qiu7Mc86MX8ehDGvn4yC3v3v97O1xnUduH0qaR2jNhVGZi2XWBW21usBMBps4Rif8UYJz/KuUeec4c+iFaM+uVTkG5rJ8f3PZ/l7seU2r1YuZfn1DADlHF/v0SV+/baMY5o1amqtc+FYH8VbdbLWpWG1yZ7lkrI3x6qitWuDz5nZ0fsj+kuGiIiIiIikSpMMERERERFJlSYZIiIiIiKSKk0yREREREQkVZpkiIiIiIhIqjTJEBERERGRVJ1ThS2CDvrNS3JGLWM5l6dZNuIvH/q8bsvJ8zpDABgo8NdcmOW1apGx2t3nbaLZhtFtNMtkeN1sp8mPWxa8is4xqtgaPq8wO3jkOZoBwHSN527Az0dc4/sxkvRWsZ52/jCf44YtfjL8DK/l9AJeS+m4/PVyRfuamli3k2brBjfTbKW5RLNu0KVZKTPa87OmUQ26lmTgItNnHMk6fDzw2/xYrdR5TXA74ff7m66/mmYAcOEeXkX7tX/iVcLzJ/g1PzU0SLOhSplmvs+vz65RmxpHfP+7XaPKNOL1hAuLi3w5AIj5ubJqFJsN/pq1Zb7/kcPHe9d4Ns0s8OrjqSo/TxjgY3M95vXpANCNjTHP4bWe3gC/NiKztbX3edDvZ2uPg35dn8kqazV7l3tpx+Ssy1n1wkb9bce4/8IGf8YlzhDNsnl+DU0M8vcpRY9fs1vW8Yr+beO8ar5UsD/fNlq58eAhXh9+/9P82Cz6/Hh7RqesVVMchkZlrNVua1Ufn+WaSowabItxKZrO1tJ8NvpLhoiIiIiIpEqTDBERERERSZUmGSIiIiIikipNMkREREREJFWaZIiIiIiISKo0yRARERERkVSdU4Xt4OAAMrneeUmhxCv9kgzvvypVeaVaGPEaxDBs0gwAGsu86tNr8B6vfIbvB9q8ChFtXuPmZMZoFoV8//NZngVGLeUyb0xFsrKbhwCKwQjPEr7/eW8DzWZqj9Bsa2acZhsLF9EscPn+t1u8znTZn6ZZvLhMMwBwYl53WS3xLHZ5vWZ9hdd55krDPT8Lui+tnvG1Jp8UkU9677XJse10mUejUzRbAr/f11/Ir7Grr9lDMwC4YPd6mo0O8KHz3/73V2i2UuPXZ6tZotniPL/GfKMKOcnwz5HqXasKm99jw0adMADkwa/ryKjbrdX5efSNqshsjldadwK+H0sdfj9ljSrwtsfH5jbsZ5MP/pqtkF8bXoWPIwMlvv9RnzrMKFz740gQBX3rma1PTV2Hpy+1wvas/Z7GehNjY412f2TBr5PLqvw6ufjSy2g2PshfMDY2NOfy2uVNY/w9g2tUWQNAGPL1ZnZN0Gylzdf7/w7XaJYkxlcmGHXCGaN2OjEq8xOzwvYs92fEx9DIOK7WvZEYFb5glbmrvGX0lwwREREREUmVJhkiIiIiIpIqTTJERERERCRVmmSIiIiIiEiqNMkQEREREZFUaZIhIiIiIiKpOqcKW7ebwOtXiefwSq0g4RWCLaMCq9XgVYDZnN2dNegM0CxvVK7lwkGalbwtNPO6vHozbvO6tWK2SjNEfP7nRLymbKrCt3Oy+gb+egDaUZ1mzcU2zY7MPkuz4cyTNBtK+HnaPM6P6YGZwzRznd7q19OyDr8W/a5dqdcxqvHa5YdpFuV4LfJKh1dP1mu9dbvtpl0dula06gHcuHfocfP8/usa7dLrt2yi2Y3v4df8jl28ehoAckU+zlz4Jl5/Gxqj6tc+9a8023/4GZo5Xb5Ss5I0x8e7RaOKdmSYX5uZYo6/HoD2Ch9H6su8frPp83V6Ht//bsgXXO50aNYyngUHTszR7Ll5/np1o+4SAGKj0rQLXms5uG6IZuUSH0cX+zxHI6NGd61IohhJn2NtVYMm7kurqbXqbZPYPpaOcU4T4zx4GX7/eZWt/PUG+PuGbpPXtC9meH12ZYBvy9NzvFr72z+o0ay5cJJmADAwuY1mbsSPadDiz/iyy493JzbOk2OMvTQBYLz3jazr5ix1ynHI1xsb6814fB+tIuYkIft/tqrdH9JfMkREREREJFWaZIiIiIiISKo0yRARERERkVRpkiEiIiIiIqnSJENERERERFKlSYaIiIiIiKTqnCpsk/kEcaa3Xisu8ior3+UVgjmjCjGXHaWZ69vVWYlRaRgb/ZLj6y+hWTbaRbO5k7xfM5vhrxcWefVv5PN6yXab71+hyOvm3LOc7aHqFM1yg0YV5hg/HzmjXnGls0SzU+3v0aw8yefGhYhX2HY7ZZp50XqaAUBilLzNLD5Os3y2QrORkb00c4PebW0Vz+l2fc06uTiLgU6+5+df/+7X6TJj23mF582/9gs0O28Pr6l1MryWGQC6XV6j7fu8vPCiS3fT7NnHeP3ylz/z7zTL+bxiMjDql+OEjzFDBX5Nb5raQDM4dsViwxi7ljp8rKh1e6+J06xPw7JZvj31LN+WbJWPTceOL9Bsps7XuW7zOM0A4ORxXo0bBnyMdR3+rFxZ4pXBnbB3Wzsdoyt4jfDgwOszJlt1s1a9p1lT+xIzAHCMSl2rqtSJszQ71uLZD5Z5ven3F47RbGiEP6fiiG9nbZmPocHx79Mss3SUZgBw0/t5he3cCV5/u32Ij5Nuge/j15/l70U84xQP5fgzuZLn93M+x+9nx+PLAUDX5+e43eLnY7nDnxNzRkU6EydW8e2P6C8ZIiIiIiKSKk0yREREREQkVZpkiIiIiIhIqjTJEBERERGRVGmSISIiIiIiqdIkQ0REREREUnVOvVW71l+CfK63Pi0a4NWDUZbXrU1Veb1kYWiQZk5sV2fNzT1Hs8Umr3T0Cjto1ulUadYOeE1vobhMM9/ny7WbLZo1m7xaM4p4TVkU8X0HgMEKr3grlnlN74m5RZp1PF4TOd3kdY7lBd4b5w3zbQlWjtJswOW1ccPFrTQDgEyOX3Nhl6+3lOdVzBsnd9Isi94K0UadXxNrycS29Sj1uZ7CMq/WvOSyi2m24+JJmkVJg2ZBxO8/APAjXhUIj18PuTIfVje/jp/zxj9/lWaZgN8PK01eqZrL8M+RLrngPJpt3caz5SY/pgDQnOU1ijMtfkxPtXjFqOfxcc3L8ArX8iSvg3zj26/m2/Kv36LZyYBXaP78+99KMwD4j3//Bs2++cCzNDthVN8G3c00c5ze/Xfitf/Zopck8PpUwMbg90nOM+rkE37tdUP+3DxbhS2M7UHCz4MDfr13jfc/C0ZFdM4Ysyod4z2F8bah3JmnWSdZoVlgHG8ACJemaTZz7CBfzqjsvuraG2m2zqj+Hy/z97CbRo33TEa1diHP3zNkjK89AIDIqGIOu/xZcGSmRrNPf+0ozaZJ9W0cGs/HF1j7o42IiIiIiLymaJIhIiIiIiKp0iRDRERERERSpUmGiIiIiIikSpMMERERERFJlSYZIiIiIiKSKk0yREREREQkVef0PRkXXfQmFIu9/fbuEO8KdsslmlUL/DsUvDz/7g0PvLcYAJ48+AjNFp47RbMjM/x7CLIZ3qlfLPMu9lzAO9yTgHclN5d513yYGL34fb7H5LRWg28LADxz9DDNygW+rVHML6NGwL/7YK6+QLPtwVaaLZ7g/czPHT1As6zPz1O1zK8LAFi/dYhmyyH/npC4yq/xkazxPSH53nsqTPg1sZYMTQyjPNh7XG7977fQZXJF/nlI4PLr2jX65t2zDH/FIh/XkoSvN4z5/bl+C/9Oj/N38+/QOP5dfq0kEX89L8u/U8bP8G74/Yf5dzbM1vh3/wDAzBz/Ho25ZT4erPT5TofTXI9f++UCHw+uvPbNNLvibVfS7BtPHKFZ69AxmpWqfJwEgHf8wlto9tST/0yz/Y98j2bXvINfN5Nbh3t+5kT2Nq4FuWwGXrb3/nVcfl8OFfl7ilbIv9OgvWKNL7azfo0GkfP4mhPw77vIGN8/sXmQ7/+eiSrNFpdqNFs2vrspiPm5mF2xv2vn/gceoNlFl11Fs3yej+nDZf4s3jQxRrMx43syqsZ3xLkOPxcDxvsp1zj3AOD7fLyrNfj5OHiMf79PZHzXmxP3H5cd4/s6Xkh/yRARERERkVRpkiEiIiIiIqnSJENERERERFKlSYaIiIiIiKRKkwwREREREUmVJhkiIiIiIpKqc6qwPe+ifSiVyj0/T7K8CjHK8LqtjNekmRfxdTpFXnUIAK3v8eq0E8d4bepih2eVcu9+nxbO8H0cyPPlxkfGaTY6yCtTGy1+3HyfV5EFHV4fCQCN2grNOnFIMzfm6210eN1jw1jnSsxrAx2X9wJmnQmaff8Qr+gdWmfX+y5leJ1ptsTPf8OoMF5Y4jV+2yYu6/lZq8GrSteSpt+A0+29R0sj/J6PwY+xVSfrGHWAYdeu4EsS6zMYfg36Rh1gdYJfR+9419to9n9m7qVZq2btBx8rF1x+364bN8af0K6w7Qb8NTMlXiNZ9Ph4MD7G7+srr9pDsze89VKaOVV+ftdvG6FZHPNKy0OHePUtALzjv11Bs127pmj26GMHaXb86DTNtuxY3/Oz8Jye+q9NAwNFZPpU4Hsevy8Xl5do1vL5clFk9NC69ue0jsPrZmHUzbpG/WtkPDf3bazS7C07jWu6y9e5bFwvUcjHkFadjxNl4/0NAFx8ae/z77TL3vAmvl6jUtbv8m11jdOExAiNKGd8DUMQ8OfZ8aPHjY0B/uORJ2j2yDR/v3Ggxq+pZZ9/1YSb6b+TiXnQXrD8qn5LRERERERklTTJEBERERGRVGmSISIiIiIiqdIkQ0REREREUqVJhoiIiIiIpEqTDBERERERSdU5ldkVB4cw0KfKNYz5XCWyWq6yvDYtTlo0K5TtCtugOUezU09/n2ZJmdd4jU1eSLNDB0/SrO0UaeY0eSVpZgOvzXOM+szp547SrNniFbUA0GrxSlUvMmpCE16pi0KNRkmWV0Eem+HVt8ND/Dxt2ryRZt0uPxdtn+87APhdnldG+H50jJpUf4VX/OXRW7fbafLau7UkCn2EYe89bAwjgFFTmzEqU8OE3yvJWYa/JOF5EPKa2sTl5zzM8nt+096tNCtODtJs+cAJmjkZfm1uunIbzX7u5p+h2fQpXpkKALOzNZrVjWs4dPjzYMPUOppt3syrwH2jQn2pzSvLN27hdZ8Zl48/zzzFzwUAlN7Nr43L9u2g2eOPPU2zdpNXc0ZB7+v1+9laU6/X4fm9Y4K1b77RN5oYVbS5/0Tlb2I8q63hznP4cjsm+PX3/p/i71OWm3zMWlqu0Ww4zw/AiQZ/hu29iFdLX/mm62gGAMMjwzQrGmNaPuH3+/Agr0gvGCc55/JxaWGev9d88ge8dvrBb3yTZg89+BDNAGApU6XZyNU/S7NWyI9b7PDnK0hlcmzULL+Q/pIhIiIiIiKp0iRDRERERERSpUmGiIiIiIikSpMMERERERFJlSYZIiIiIiKSKk0yREREREQkVedUzuZ6z//z45KIV3wFAa/XCyNeqRbneNVjXLerPJ0GryYMG6doNjzGKx27c3y55iyvWw1jXpsXNHil7ILxel6eV3a223Ujsyts6y1+3DzXuFQ8fh43buPLjU/xWs6BPH+5xKglbQYzNNu2dTPNMtEG/oIAWv6TNHMzx2nmR7w2t1Tmdbtxn0u838/WIueH//fjwoDvYCbDr/nYaORstfg4YlXU/nDNNIlCvq3ZAq8K9I2PdYpVvo/l9VWazTT5PT80xO+x8e28JnJoa29V+WmF9VtoBgA7HJ4Hbf48aHSMMd94xriuVa/Nz2He44PMurFRmlWMKsxclteLAsBAZYhmF1+xk2bD//wAzaxxodinfjT2/xOdrK8RfhT1rVVPjPOdyfBnseMZ9bZGU2d4ls9pc46x3pCveKKco9k7rziPZhurfLnWCq9hn6hWaDZsvN9YV7qKZrt37abZ4BCviAYA3+djQd7jx801KmwXZ3n19rNHeyvjT/vWI4/R7NuPPUGzQ4efoVndeO8Xwf6KhuErb6JZO+JjkxPysTfrGddxQjL28x+jv2SIiIiIiEiqNMkQEREREZFUaZIhIiIiIiKp0iRDRERERERSpUmGiIiIiIikSpMMERERERFJ1Tl12XX8Drw+9Xd+m1eKdfw2zaKEZ2G4yDPwKi4AaC3zSkc3zyvlMiV+OGrzvHJsftqoME14vWsYtWhWrk7x5TpGnafP19lqz9EMADrRLM2cHK/lzGR5pey6jXw/dpzPK4NnFniFb463csJx+XJ+k19Tk8Ov4ysFAHc9jZIyvzYO/mCJZlNjEzQr5Qd6ftb27Ot+rWj7CVy/95rxjBq9XIbfmyH49dfq8mPW7vBxAgBc1/oMhr9myeP1r5HD1+m6fKyoTvG62dDj96ab5TWtIyN8nYFRGevD7lJ2Q14/6VjLGlW0vlGF7iRGTahxnnIer/ssD/IK2+F1/HhPbeDjBABELq+4Hd3Mt3Xzdr49SWQ80/pUqHpGrepa4SCB0/fc8uvWMSqrc0ZF+9AAv066faq4X7Q1Id8eL+DX+8YyHyd2GWNBu2PcJxG/L0sFfl1u2cYrqd3zePV7PsfHnsh4XwgA9XleRf/ooUM0e/JJXjX/+BO8bvbwM0bdbN2omzXOb9ynYvk0j9/qKIzy9wUAUBnjxzyxtifmWWLW5vavhY6M/Xsh/SVDRERERERSpUmGiIiIiIikSpMMERERERFJlSYZIiIiIiKSKk0yREREREQkVZpkiIiIiIhIqs6pwjaKHURxb2VbbNVx5So0C7pNmvm1aZotBjX+ggAGRqs0+6mfeTPNTrZ43eixxRM0G9vOq9pio7IyCnjdrI8GzUqDvCZx9hg/bh3frrDdeckID4v8JC8sL9CsOl7k63R4FWS7wasBR8Z43V6Y8HO4bmKIZmNj9nzbddfRrNburZs9s94qX2/e48vNnuyt+Ou0fjIqbDsh4PVpMnXj/lV5ABAYtdVBYFSmOkaFaZ5XUwJAFPKKvtgY9DpGbW7HN/bRGI0rQ7wW18vx+sFsgd9/+Sy/prstvp2hy483AMRdPq5lYqN+22hETIyq0DDg1YytNt+WrsvP/+Iifza1jZrwgZIx3gGYX1ymWWhUmpYqfOxqNvlyrVbvjdZu2xXEa0Hey8LrV91sNHGev36cZtunxmi2ZaRAs1qDXycAsGzkuZBXVlcC/hzzO/x8d7v8XqhU+PNmoE9l+mkOHwpQKvFjs7TEK/G/+tUH+UoBfP3rD9PswA8O02x+wThuRrV2ZDx7EBlvcI2KbM/jA7qX48c7O7rZeD3AMZZ1Y6PC2NieJOH7nyT9r6kkWd04or9kiIiIiIhIqjTJEBERERGRVGmSISIiIiIiqdIkQ0REREREUqVJhoiIiIiIpEqTDBERERERSdU5Vdj6QYxsnwpGx1iNExvzmIgvly3wWthCldfiAkC5yfP6M8dodtmFvMZu+4VGN547QSO/zff/2//Bt2V+nte7Fit8/1ptXn07NMLXCQB7L99CsyOzB/mCFV4vuX7zJM2Gh6doVi7xmt52eIpm9RavqYsTvv/H579HMwAYqVp1n7xecqg4TLOgbVQRdnr3o9td+9WTANDyQ8DvrcULA16/l8ny+6her9GsYlQsjo2O0gwAkiyvJ0wSnrU7fD/ard5q4tMij9cIRjGvpnRz/P6rNVZo9uwRXvc4PMXHGK/IxxgASCJ+ncYBH0frHX5sOj6/r61zEQR8W0Lj/D5nVIEv1/kxdY3rFABWGvzYuQmv1G13+LY+fYjXqy+v9O5/q8GvpbXijRduR36gt9a5OsCP0/axQZqVIj4WD2X48QoyxvsCAO0Sf+aETV5v220Z15FrZEZl90COL5d1+XKN+ZM8O8nvha88/DjN/vFzX6AZAMzP8rp9q202Nj43jx1+rlyjjjUBf0Eny9+n5oxa4FyOXxeZ8Q00e/4X+DPN6gGPYVW982cIErbO1Y0j+kuGiIiIiIikSpMMERERERFJlSYZIiIiIiKSKk0yREREREQkVZpkiIiIiIhIqjTJEBERERGRVJ1ThW3kR4iyvXVWUafDXyDDq9GcDK8srAwW+Xa0azQDgBPPHaDZ0987xF+zcAHNOiMzNGsb1Zujxc00c2N+3MaGz6dZvliiWTfgdWtD66o0A4Ag5PtRr8/TbMNGXv3rRHwfH/j3h2mWHeD7Mb6Z17TlPF4pN3OS1+L50QLNAGCxwSt1Rwq8cm6ozGsTwwyf44d9evraTX5+1pJGs4kIvecwl+UVnvkMr/zL5fg5dx2jXtvIAMD3+bXbarVoFgT8+gQfDq0IQcLrAr0Cv45qNV5T+4Uvfplmg6Nvp9nW83qrQ18oglEbG/H9aLV5xWLdqH4NQ77OrFEV6cY8mz7FxwM/5Oc3kz/LNWUsGxk1vf3Gg9NOPscrRhcWeo9bu8mv67XiFy7dglKfsTWX53fRs9N8/P/6Aw/S7MJx/l7EMcYsAPCNStnDB3lt+o6d/PnvGtWhtROHadZcWqbZzPQszZ4+zNd5bJ7fJ+EAr68f2bCNZgCQGM/xqE/9+ZnXND427xrv08JWnWbFLK93dWm9K9Bp8YriqMAr8YvD4zQD7Irw0KiwTfo8c0+zKmwjMmbHxnj1QvpLhoiIiIiIpEqTDBERERERSZUmGSIiIiIikipNMkREREREJFWaZIiIiIiISKo0yRARERERkVSdU4VtNhsim+2tzwoavM4xk/No1ol4LerJU9+h2Q8e+S7NAKDi8YrFUlCg2YH799Msv5VXfC0YFb4D26s027pxgGbHT/F6MKvCLZPjlXoTRvUrAMQJr4mMW3y9Ay6vmzty8Gmaff3h4zTbuIdfmnGFz42z4SjNwhW+DyNj9q1w9Aiv8fvB8iLNfubaN9NsciOvRmyGvdWAGfxkVNgWcjkU873nolDg5yeX5ee8MDxEs3yGr7Pdtqs8l2u88rHd5mNe2agtToyKQasW1/o4qDTEx5HXX76PZkeP8XvzU//jf9Lsp95yBd8YABfs3USzoQk+ViQJf1ZkPD5uO0Y1Y2iMlXPLNZodOnyUZta5iIyqYQCIYv4cafv8/i6WjTGvzseuZrt3ne0Or8BcK9pJBm7Su9+LRj3vD6Z5TelD3/s+zY4bdeqjZT6GA8BQll8Pg5UKzYoVPqYdn+bvm55+llfKPrr/Mb7ccV6DXO/w/UeG38/XvX4Pzd6++zy+TgBGKzcKRmX5iVlexXt8lh+3lQb/OoWnnuRVwwcf/TrN4sio2p/ayZcz6nsBIGrx9xtw+BjqGnXLdoVt//2w9u9Fr7uq3xIREREREVklTTJERERERCRVmmSIiIiIiEiqNMkQEREREZFUaZIhIiIiIiKp0iRDRERERERSdU4VtrXgOPygty7R7/L6r6bRyniqxqtoTy49QLP5mRpfKYDJ7IU0GzUqvlbafL3ZGV5LmWvzmrrj0VM023XdFpotxHxblk7y0zY2xWvF9l5uzykLJV4TOT+/mWZzc7xSrVTmNX27d2+k2eBGfuEkEb/eooAfm5kTTZo1F+1bwe/yasRag1ednti9jmalyjjNpud7K5y7rdVVxr3WZREh26d21I14hWfB41WRCRKexbx+MY74cgCQz/P7IWdURReLJZrV67wmOor4NV8Y4NsSgo8/23fxMeb8103Q7Auf4ePvP/+vh2gGAD/T5LW5l/00357Y5fdgGPBr33H4uJYkvJpxdpbXfdYb/H7ftIWPhfUGr0kFgJnZOZpljP0fGuWZm+XjSKPZO+Z1Wrwefa349nQNhVLvNdHt8H2bPsXPzQBvgcZiiy93ZIZXpgLA+gqv0/+Fm3i9+Z7XXUyzXJE/U0eneH30+AW7aHatUfU8PsLrdKtF45ot8oOaL/DxDABKRp51+f3e6PLzv9jiz5fpGr/f/2OMP8PbMX+GnFzg40vi8eVai7xOGAAiPqShOMCvt8Tl732tCtsk6b+t7Oc/Tn/JEBERERGRVGmSISIiIiIiqdIkQ0REREREUqVJhoiIiIiIpEqTDBERERERSZUmGSIiIiIikipNMkREREREJFXn9j0ZzVPoJr39xc2VGbpM1ObfTVBrHKZZ3OHfhTA0YPfztpYP0aw0wruC3TL/LoxsgfcPDwa8R9qd4F3Rw2O8C3pwiPcWP3ewRjMHfP8WT9lzym44T7OJSf6dFsdO8H7/hXl+/pMs760eN2q083l+bKy+526Xf2fC9FMr/AUBlLJ8g86/ZBvNGsZ3aMwv8es4m+/tgI+in4zvyQj9DsI+pz70+fHI8MsaAwP8OzSyWf59Fp7xvQQAkDOWtTrCra7+2Ofn0I2yNAu7fLkgMLrhl3hX+1Vv2U2zK990Gc2++cCTNAOAI88ep9nksTzN8mU+xg4NjdDMD/g4srLCx596g49bO/dsp1m1OkmzwWHjQgVQW+bjjGf02G/euYFmnRYf11t+7/53jeO1VtSWash3e7/bIeRf9wAnCmiWc/i97rv8mp0csd+LbNxxCc3Ou/hymlWq/LswXON7IgbL/Pk3Mcq/JyNnfPeCm/DnpmN8R5EDvtLobN+xEPExzQ/59rjG96AN5Pj4OjHEnwVXXsbHwny5SrP/++9fodlzJ5+lWRTz974AEBrvRVyP72MG/Bp3X8J3aFjfQfWida/qt0RERERERFZJkwwREREREUmVJhkiIiIiIpIqTTJERERERCRVmmSIiIiIiEiqNMkQEREREZFUnVOFbbt+Coh669wcb44uk610aDY0YNSNPsOrXytjvIoOAIJ1izRzsrwKcf3IRTQ7foLX9C4/zWtK92zYQ7Nymde4bdrIawYXTvL9e+b7fJ3tFbte0RvglY65Iq9Vm1jPj+nMcV6L2415vSSMijsHvDptsMrrBrdtH6bZ3KFjfFsAhAGvjVtZ5HV7M9O8srIb1Wg2uq7a87PI6mdcQ1rtEInbew8HIb+vg5B/HuL7fBwZKPLr6KyVwAlfr+fxoTMyamqDNt/HVoOf31MneBXtxNg6mg0PVfnrGdW3W143RrOlDs8AIJfh56phNEUHLt//XJFnUWhUH+f5c2RiA6/l3noeH0d8n2+Lc5aP7fyAj8HLK/w5UirzmuZiwdj/gd5Ky9AYP9eKycEBFEqlnp8Hxj0dOFWa5Us8e47fJsgN8XsPAN78lktpNlLhlc2BUdMaJ3wfG8apte7LCm83NWWMMdL1+Ot5rtGZC9g3Usz3P4n5eq3acaOJF9VBXie8azuvr//+wSmanTjBK2xDY/8Au+o6Mc6HtY9WHS1bLF5lpb7+kiEiIiIiIqnSJENERERERFKlSYaIiIiIiKRKkwwREREREUmVJhkiIiIiIpIqTTJERERERCRV51Rh21l6Cuj0VuJ5ed7x1nV4NVauwmtBpy5cT7MgsKuzwjyfO8XLgzRbmeUVro0az9rTvN71u99+imajg/zwu1leb/eGa3gt49ZtEzQbGTO6+AAMjvPaxuIoP1euO0mz+RO84m128RDN4vxzNEPQew3+aEHexZcb4JnDdx0AUCkblYJxnWYNo5Y0NCo7C4Xeyspua3WVca91yyttdI2Kxn6iiFc6t9r8uDgxP8bdDr9vAbumNl/g90Muxy+mRotXegdGFWtlhNcoXvVTvCZz81Zeo+hm+bGpjPTWg552yeW8lhsABnJ8fBoc5ONvF/x8eC4/F45RzZk36h6tSseOb5yngNcQF4q8ahYAKhV+HnN5ft14Ob7/fpeP6/3WGUdr/7PFraODGCj3Hsso5uNELcPHnJZR9bxzmFefb7/0YpoBwIYNm2nmG9eR5xlVrNYLGmEc8zBJ+H2Ssapojc+pHbOm1tyLl1w3a4mNmlbr2OQz/NgMDvDnwI7N/NwffuYZmh1fNHq+ASQZ472Yw98bOY5RN2ycq4Qcm7OUEP9o3av8PRERERERkVXRJENERERERFKlSYaIiIiIiKRKkwwREREREUmVJhkiIiIiIpIqTTJERERERCRV51RhO1HMoFjsXaSV52VWGfC6rcSoHswN8zpDf4nXAAJAa5ZnSwcW+Gs2eG3sYHeUZmGW70c34ZV6ccSrHpdO8QrFesDXed62dXxbAl5ZCQCLx/ixcRv8oBbKfP+3beMVfxMbeN3jUofXOc7N8crY2OfXm5fj1+nFV26lGQB40RJ/TRj1xiG/jh3j3nDc3tq4fj9bi2LkEKO3TjibMaqJXZ41mvwYRz6v92w2mvz1AHjG+DRc5bWGnlExCKOmtDDA93HSqDAtrWvQrFjh+xDFPMvEfDszw8Z5AlDK8/rbbIbvR9Dm58qN+L0bGpXmK/VlmnWNa8Oqxc0Y5yI5SzNzvmAc1yw/rs2WcWxcozK53vsc6RrHea0YLRdQqvQ+PwKfn5tGiz//Bi7iNdCb1vHa5V3njdEMAHLG57hulm9r1ugHzRqtzEbbKhyjdDTj8GeL1URrtKLCdY19N+tteW0qACTg93tivMUJjDAxtscDP6ilIr/39r5uN826Rg/vl772CM0AYHaZvzd0jRPiOdbfFPhytPrWWd30QX/JEBERERGRVGmSISIiIiIiqdIkQ0REREREUqVJhoiIiIiIpEqTDBERERERSZUmGSIiIiIikqpzqrAdCasohb3Vk90pXvE2e7xmZKdoFg7wmr2MP0QzAHBP8IqzwqLRcWZUASLk+1jawatoR7fzqjLP2o/ZGo1mnuHHLVridarj285y3GJe1VbsTtFscZlXgWaj52g2OjFBs8mRPTSLOidoduwEPzbFMj9Pw2PGuQcQdngtacbqG5zn57+7zK/ToNN7nQYd/vtriR8kcIPe4xIGAV2m3eZZs8mv+Xy2d7w6zcvwqtXnc54lDr9XuiE/T92Id5wGPr+PrNrG/CDf0NDhdYe+cT1FXb6d3aZdgep7vGLbqimeX+Q12SPDVZrFCb/H5qfnaNbx+Xaum5qkWWTURC6u8Krr5xlVocYFN33SqNA26j6juPcc+x2+32tFEnWRhL3XYafLr82iUTV/4Y7NNFs/zMf+omuPya5nVYoaleRG5BrXu7VKq97UMdaZGLsYG7XqibHOMLI/344i49kY8fU2fT5uNTr82mgb412U8PuybYz1kcfHuqmNW2g2OnyUZgCwsHKMZtY15Rj92k5iVQqT7Gx93T+kv2SIiIiIiEiqNMkQEREREZFUaZIhIiIiIiKp0iRDRERERERSpUmGiIiIiIikalXtUqdbAlqklcJvGf+r/TZvsuh0eGNM6PAWqAxf7Pllu3zZrm9UJVhNEYGxTvDM6RjtUlm+I77P1xkYjQa+z+eN3T6NRS8UxsZ+tI39N453p2U0BjX5tREmxnXT4q/nt/mxcT1j/4OztF1YTTzW+ejwBobYaGfotnrX2f3hvlmtHa9lp7e72+4/XrisxeIs2PoAIOnTYvWj7bGbYTxeIIWMEVptPx2zNYVnVrsUjMx1+HVt3StWu5RvHG8ASIxGnShjXPNG61HHeE2rXco3njG+0WbWNZ5bXmiMscZyANAxnpWuZ40jfL3n3i71/H6vxXHkzHuRRr1v3jKOf6vLj2/WaKFrZvg6I+OcAYBrjBOecW96xqnxjdAas6x2Kc+qszJY44tjZMlZPt/ud92eZrVLtYx2qabVLmUsZ7VLdYxnfyto8+VaDZqFXd4ICABxwPfDyfBttZrHHPPZ2z+Lg+e382zjiJOsYqQ5fvw4Nm3adLZfE5FXwLFjx7Bx48ZXezPOmcYRkdeOtTiOaAwReW052ziyqklGHMc4efIkKpUKHGM2LCIvnyRJUK/XsX79erju2vsvHTWOiLz61vI4ojFE5LVhtePIqiYZIiIiIiIiq7W2PsYQEREREZHXPE0yREREREQkVZpkiIiIiIhIqjTJEBERERGRVGmS8RPs6NGjcBwH+/fvP+dlr7nmGnz4wx9OfZtERETkvwbHcXDPPffQ/P7774fjOKjVaq/YNskrR5OMNeyWW26B4zhn/hkdHcWNN96I73znOwCATZs2YXp6GhdddNGrvKUi8mq65ZZbcNNNN/X8XA94EfnPmJubw6//+q9j8+bNyOfzmJycxA033ICHHnpoVctfffXVmJ6extDQ0Mu8pfJq0CRjjbvxxhsxPT2N6elpfOUrX0Emk8HP/uzPAgA8z8Pk5CQy5FsgkyRBGNrfAi4iwvi+/Q3XIvKT7V3vehcef/xx/P3f/z2eeuop3HvvvbjmmmuwsLCwquVzuRwmJyf1vSc/oTTJWONOf3IwOTmJSy65BB/96Edx7NgxzM3N9fznUqc/tbzvvvtw6aWXIp/P42tf+xqazSY+8IEPoFwuY2pqCn/xF3/x6u6UiLwqPv/5z+PCCy9EPp/H1q1be8aCrVu34o477sAHPvABDA4O4td+7dfg+z4++MEPYmpqCoVCAVu2bMEf//Efn1mmVqvh1ltvxdjYGAYHB3HdddfhiSeeeKV3TURSVqvV8OCDD+JP//RPce2112LLli244oor8LGPfQw/93M/d+b35ufn8c53vhMDAwPYuXMn7r333jPZj/819a677kK1WsU999yDnTt3olAo4IYbbsCxY8de6d2TFGiS8ROk0WjgH//xH7Fjxw6Mjo7S3/voRz+KP/mTP8GBAwewd+9e3HbbbXjggQfwL//yL/jSl76E+++/H4899tgruOUi8mp79NFHcfPNN+O9730vvvvd7+L3f//3cfvtt+Ouu+560e/9+Z//OS6++GI8/vjjuP322/GJT3wC9957L+6++24cPHgQ//RP/4StW7ee+f13v/vdmJ2dxX333YdHH30U+/btw0//9E9jcXHxld1BEUlVuVxGuVzGPffcg263S3/vD/7gD3DzzTfjO9/5Dt7+9rfj/e9/v3n/t1ot/NEf/RH+4R/+AQ899BBqtRre+973vhy7IC+3RNasX/zFX0w8z0tKpVJSKpUSAMnU1FTy6KOPJkmSJEeOHEkAJI8//niSJEny1a9+NQGQ3HPPPWfWUa/Xk1wul9x9991nfrawsJAUi8XkN3/zN1/J3RGRl8mPjxWn/ykUCgmAZGlpKXnf+96XXH/99S9a7rbbbkv27Nlz5t+3bNmS3HTTTS/6nQ996EPJddddl8Rx3PO6Dz74YDI4OJh0Op0X/Xz79u3J3/zN36S4hyLyavjc5z6XDA8PJ4VCIbn66quTj33sY8kTTzxxJgeQ/M7v/M6Zf280GgmA5L777kuS5EfvS5aWlpIkSZK/+7u/SwAk3/zmN88sc+DAgQRA8vDDD78yOyWp0V8y1rhrr70W+/fvx/79+/Gtb30LN9xwA972trfh2WefpctcdtllZ/7/w4cPw/d9XHnllWd+NjIygl27dr2s2y0ir6wXjhWn//n0pz99Jj9w4ADe+MY3vmiZN77xjXj66acRRdGZn71w/ACe/x+V79+/H7t27cJv/MZv4Etf+tKZ7IknnkCj0cDo6OiZTz3L5TKOHDmCw4cPv0x7KiKvlHe96104efIk7r33Xtx44424//77sW/fvhf9BXTv3r1n/v9SqYTBwUHMzs7SdWYyGVx++eVn/v2CCy5AtVrFgQMHXpZ9kJdP//9FsKwZpVIJO3bsOPPvn/70pzE0NIRPfepTuPXWW+kyIvJfy4+PFQBw/Pjxl7SeF9q3bx+OHDmC++67D1/+8pdx8803461vfSs+97nPodFoYGpqCvfff3/PeqrV6jm/toi89hQKBVx//fW4/vrrcfvtt+PWW2/F7/3e7+GWW24BAGSz2Rf9vuM4iOP4VdhSeaXpLxk/YRzHgeu6aLfbq/r97du3I5vN4uGHHz7zs6WlJTz11FMv1yaKyGvQ7t27e2onH3roIZx//vnwPM9cdnBwEO95z3vwqU99Cp/5zGfw+c9/HouLi9i3bx9mZmaQyWSwY8eOF/2zbt26l3N3RORVsmfPHjSbzZe8fBiGeOSRR878+8GDB1Gr1bB79+40Nk9eQfpLxhrX7XYxMzMD4PnJwSc/+Uk0Gg284x3vWNXy5XIZv/Irv4LbbrsNo6OjGB8fx8c//nG4ruafIv+VfOQjH8Hll1+OO+64A+95z3vwjW98A5/85Cfx13/91+Zyf/mXf4mpqSm8/vWvh+u6+OxnP4vJyUlUq1W89a1vxVVXXYWbbroJd955J84//3ycPHkSX/jCF/DOd76z5z+9EpG1Y2FhAe9+97vxy7/8y9i7dy8qlQoeeeQR3Hnnnfj5n//5l7zebDaLD33oQ/jEJz6BTCaDD37wg3jDG96AK664IsWtl1eCJhlr3L/9279hamoKAFCpVHDBBRfgs5/9LK655hocPXp0Vev4sz/7szMTk0qlgo985CNYXl5+GbdaRF5r9u3bh7vvvhu/+7u/izvuuANTU1P4wz/8wzP/yQNTqVRw55134umnn4bnebj88svxxS9+8cwHFV/84hfx8Y9/HL/0S7+Eubk5TE5O4i1veQsmJiZegb0SkZdLuVzGlVdeib/6q7/C4cOHEQQBNm3ahF/91V/Fb//2b7/k9Q4MDOC3fuu38L73vQ8nTpzAm9/8Zvzt3/5tilsurxQnSZLk1d4IEREREfmv7a677sKHP/zhM9+bIWub/psYERERERFJlSYZIiIiIiKSKv3nUiIiIiIikir9JUNERERERFKlSYaIiIiIiKRKkwwREREREUmVJhkiIiIiIpIqTTJERERERCRVmmSIiIiIiEiqNMkQEREREZFUaZIhIiIiIiKp+v/Y93DugucZuQAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 1000x1000 with 9 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# View some images of the training set\n",
+    "classes = ['Airplane', 'Automobile', 'Bird', 'Cat', 'Deer',\n",
+    "           'Dog', 'Frog', 'Horse', 'Ship', 'Truck' ]\n",
+    "\n",
+    "plt.figure(figsize=(10, 10))\n",
+    "for i in range(9):\n",
+    "    plt.subplot(3, 3, i + 1)\n",
+    "    plt.xticks([])\n",
+    "    plt.yticks([])\n",
+    "    plt.grid(False)\n",
+    "    plt.imshow(x_train[i])\n",
+    "    # Convert the label to a number and use it to get the class name\n",
+    "    plt.xlabel(classes[y_train[i][0]])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Model Architecture (CNN)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │         <span style=\"color: #00af00; text-decoration-color: #00af00\">9,248</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">36,928</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">66,048</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">5,130</span> │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m896\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │         \u001b[38;5;34m9,248\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m36,928\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │        \u001b[38;5;34m73,856\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │        \u001b[38;5;34m66,048\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m5,130\u001b[0m │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">210,602</span> (822.66 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m210,602\u001b[0m (822.66 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">210,602</span> (822.66 KB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m210,602\u001b[0m (822.66 KB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
+    "\n",
+    "# Define the model\n",
+    "model = Sequential()\n",
+    "\n",
+    "# Define input form with Input()\n",
+    "model.add(Input(shape=(32, 32, 3)))\n",
+    "\n",
+    "# First convolutional layer\n",
+    "model.add(Conv2D(32, (3, 3), activation='relu'))\n",
+    "model.add(Conv2D(32, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
+    "model.add(Dropout(0.25))\n",
+    "\n",
+    "# Second convolutional layer\n",
+    "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
+    "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
+    "model.add(Dropout(0.25))\n",
+    "\n",
+    "# Third convolutional layer\n",
+    "model.add(Conv2D(128, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
+    "model.add(Dropout(0.25))\n",
+    "\n",
+    "# Flatten outlets and add dense coatings\n",
+    "model.add(Flatten())\n",
+    "model.add(Dense(512, activation='relu'))\n",
+    "model.add(Dropout(0.5))\n",
+    "model.add(Dense(10, activation='softmax'))  # CIFAR-10 has 10 classes\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# Display the model summary\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Model Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/5\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m725s\u001b[0m 456ms/step - accuracy: 0.2365 - loss: 2.1158 - val_accuracy: 0.4904 - val_loss: 1.4845 - learning_rate: 1.0000e-04\n",
+      "Epoch 2/5\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m846s\u001b[0m 541ms/step - accuracy: 0.4483 - loss: 1.5715 - val_accuracy: 0.5254 - val_loss: 1.3541 - learning_rate: 1.0000e-04\n",
+      "Epoch 3/5\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1001s\u001b[0m 640ms/step - accuracy: 0.4965 - loss: 1.4370 - val_accuracy: 0.5481 - val_loss: 1.2880 - learning_rate: 1.0000e-04\n",
+      "Epoch 4/5\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m970s\u001b[0m 620ms/step - accuracy: 0.5264 - loss: 1.3540 - val_accuracy: 0.5589 - val_loss: 1.2497 - learning_rate: 1.0000e-04\n",
+      "Epoch 5/5\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m524s\u001b[0m 335ms/step - accuracy: 0.5441 - loss: 1.3153 - val_accuracy: 0.5728 - val_loss: 1.2181 - learning_rate: 1.0000e-04\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n",
+    "\n",
+    "# Define callbacks\n",
+    "early_stopping = EarlyStopping(\n",
+    "    monitor='val_loss',  # Monitor validation loss\n",
+    "    patience=10,         # Wait 10 epochs before stopping\n",
+    "    restore_best_weights=True  # Restore the best weights at the end\n",
+    ")\n",
+    "\n",
+    "reduce_lr = ReduceLROnPlateau(\n",
+    "    monitor='val_loss',  # Monitor validation loss\n",
+    "    factor=0.2,          # Reduce the learning rate by a factor of 0.2\n",
+    "    patience=5,          # Wait 5 seasons without improvement before cutting back\n",
+    "    min_lr=1e-5          # Lower limit for learning rate\n",
+    ")\n",
+    "\n",
+    "# Training the model\n",
+    "history = model.fit(\n",
+    "    x_train, y_train,                 # Training data\n",
+    "    epochs=5,                         # Maximum number of epochs\n",
+    "    batch_size=32,                    # Lot size\n",
+    "    validation_data=(x_test, y_test), # Validation data\n",
+    "    callbacks=[early_stopping, reduce_lr]  # Add callbacks\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Display the results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Accuracy graph\n",
+    "plt.figure(figsize=(12, 4))\n",
+    "plt.subplot(1, 2, 1)\n",
+    "plt.plot(history.history['accuracy'], label='Accuracy')\n",
+    "plt.plot(history.history['val_accuracy'], label='Val Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "\n",
+    "# Loss graph\n",
+    "plt.subplot(1, 2, 2)\n",
+    "plt.plot(history.history['loss'], label='Loss')\n",
+    "plt.plot(history.history['val_loss'], label='Val Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "313/313 - 116s - 371ms/step - accuracy: 0.5728 - loss: 1.2181\n",
+      "Test Accuracy: 0.5728\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the model on the test set\n",
+    "test_loss, test_accuracy = model.evaluate(x_test, y_test, verbose=2)\n",
+    "print(f\"Test Accuracy: {test_accuracy:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m133s\u001b[0m 85ms/step - accuracy: 0.6354 - loss: 1.0396 - val_accuracy: 0.6768 - val_loss: 0.9376 - learning_rate: 0.0010\n",
+      "Epoch 2/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 88ms/step - accuracy: 0.6485 - loss: 1.0098 - val_accuracy: 0.6631 - val_loss: 0.9740 - learning_rate: 0.0010\n",
+      "Epoch 3/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 90ms/step - accuracy: 0.6595 - loss: 0.9846 - val_accuracy: 0.6916 - val_loss: 0.8936 - learning_rate: 0.0010\n",
+      "Epoch 4/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m147s\u001b[0m 94ms/step - accuracy: 0.6642 - loss: 0.9583 - val_accuracy: 0.6951 - val_loss: 0.8808 - learning_rate: 0.0010\n",
+      "Epoch 5/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m147s\u001b[0m 94ms/step - accuracy: 0.6744 - loss: 0.9472 - val_accuracy: 0.6905 - val_loss: 0.9061 - learning_rate: 0.0010\n",
+      "Epoch 6/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m196s\u001b[0m 90ms/step - accuracy: 0.6799 - loss: 0.9331 - val_accuracy: 0.6967 - val_loss: 0.8795 - learning_rate: 0.0010\n",
+      "Epoch 7/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 89ms/step - accuracy: 0.6796 - loss: 0.9182 - val_accuracy: 0.6966 - val_loss: 0.8921 - learning_rate: 0.0010\n",
+      "Epoch 8/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 90ms/step - accuracy: 0.6899 - loss: 0.8993 - val_accuracy: 0.7088 - val_loss: 0.8477 - learning_rate: 0.0010\n",
+      "Epoch 9/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m149s\u001b[0m 95ms/step - accuracy: 0.6951 - loss: 0.8849 - val_accuracy: 0.7154 - val_loss: 0.8238 - learning_rate: 0.0010\n",
+      "Epoch 10/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m153s\u001b[0m 98ms/step - accuracy: 0.6955 - loss: 0.8884 - val_accuracy: 0.7039 - val_loss: 0.8861 - learning_rate: 0.0010\n",
+      "Epoch 11/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m203s\u001b[0m 98ms/step - accuracy: 0.6949 - loss: 0.8836 - val_accuracy: 0.7210 - val_loss: 0.8218 - learning_rate: 0.0010\n",
+      "Epoch 12/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m154s\u001b[0m 98ms/step - accuracy: 0.6992 - loss: 0.8769 - val_accuracy: 0.7138 - val_loss: 0.8368 - learning_rate: 0.0010\n",
+      "Epoch 13/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m162s\u001b[0m 104ms/step - accuracy: 0.7022 - loss: 0.8629 - val_accuracy: 0.7170 - val_loss: 0.8269 - learning_rate: 0.0010\n",
+      "Epoch 14/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m194s\u001b[0m 99ms/step - accuracy: 0.7012 - loss: 0.8690 - val_accuracy: 0.7347 - val_loss: 0.7919 - learning_rate: 0.0010\n",
+      "Epoch 15/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m164s\u001b[0m 105ms/step - accuracy: 0.7111 - loss: 0.8441 - val_accuracy: 0.7232 - val_loss: 0.8138 - learning_rate: 0.0010\n",
+      "Epoch 16/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m178s\u001b[0m 114ms/step - accuracy: 0.7028 - loss: 0.8631 - val_accuracy: 0.7351 - val_loss: 0.7844 - learning_rate: 0.0010\n",
+      "Epoch 17/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m202s\u001b[0m 114ms/step - accuracy: 0.7157 - loss: 0.8308 - val_accuracy: 0.7225 - val_loss: 0.8144 - learning_rate: 0.0010\n",
+      "Epoch 18/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m156s\u001b[0m 83ms/step - accuracy: 0.7138 - loss: 0.8378 - val_accuracy: 0.7266 - val_loss: 0.8047 - learning_rate: 0.0010\n",
+      "Epoch 19/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m185s\u001b[0m 119ms/step - accuracy: 0.7155 - loss: 0.8318 - val_accuracy: 0.7256 - val_loss: 0.8144 - learning_rate: 0.0010\n",
+      "Epoch 20/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m155s\u001b[0m 99ms/step - accuracy: 0.7158 - loss: 0.8292 - val_accuracy: 0.7311 - val_loss: 0.7905 - learning_rate: 0.0010\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n",
+    "\n",
+    "# Define callbacks\n",
+    "early_stopping = EarlyStopping(\n",
+    "    monitor='val_loss',  # Monitor validation loss\n",
+    "    patience=10,         # Wait 10 epochs before stopping\n",
+    "    restore_best_weights=True  # Restore the best weights at the end\n",
+    ")\n",
+    "\n",
+    "reduce_lr = ReduceLROnPlateau(\n",
+    "    monitor='val_loss',  # Monitor validation loss\n",
+    "    factor=0.2,          # Reduce the learning rate by a factor of 0.2\n",
+    "    patience=5,          # Wait 5 seasons without improvement before cutting back\n",
+    "    min_lr=1e-5          # Lower limit for learning rate\n",
+    ")\n",
+    "\n",
+    "# Training the model\n",
+    "history = model.fit(\n",
+    "    x_train, y_train,                 # Training data\n",
+    "    epochs=20,                        # Maximum number of epochs\n",
+    "    batch_size=32,                    # Lot size\n",
+    "    validation_data=(x_test, y_test), # Validation data\n",
+    "    callbacks=[early_stopping, reduce_lr]  # Add callbacks\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Salvar o histórico de treino\n",
+    "import pickle\n",
+    "\n",
+    "with open('training_history.pkl', 'wb') as file_pi:\n",
+    "    pickle.dump(history.history, file_pi)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Carregar o histórico salvo para análise\n",
+    "with open('training_history.pkl', 'rb') as file_pi:\n",
+    "    saved_history = pickle.load(file_pi)\n",
+    "\n",
+    "# Plotar o histórico de treino\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.plot(saved_history['accuracy'], label='Train Accuracy')\n",
+    "plt.plot(saved_history['val_accuracy'], label='Validation Accuracy')\n",
+    "plt.xlabel('Epochs')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Display the results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Accuracy graph\n",
+    "plt.figure(figsize=(12, 4))\n",
+    "plt.subplot(1, 2, 1)\n",
+    "plt.plot(history.history['accuracy'], label='Accuracy')\n",
+    "plt.plot(history.history['val_accuracy'], label='Val Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "\n",
+    "# Loss graph\n",
+    "plt.subplot(1, 2, 2)\n",
+    "plt.plot(history.history['loss'], label='Loss')\n",
+    "plt.plot(history.history['val_loss'], label='Val Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Model Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "313/313 - 6s - 20ms/step - accuracy: 0.7351 - loss: 0.7844\n",
+      "Test Accuracy: 0.7351\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the model on the test set\n",
+    "test_loss, test_accuracy = model.evaluate(x_test, y_test, verbose=2)\n",
+    "print(f\"Test Accuracy: {test_accuracy:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Metrics Calculation (Precision, Recall and F1-Score)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m114s\u001b[0m 362ms/step\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.68      0.72      0.70      1000\n",
+      "           1       0.69      0.70      0.70      1000\n",
+      "           2       0.57      0.48      0.52      1000\n",
+      "           3       0.47      0.50      0.49      1000\n",
+      "           4       0.57      0.57      0.57      1000\n",
+      "           5       0.63      0.53      0.57      1000\n",
+      "           6       0.65      0.73      0.69      1000\n",
+      "           7       0.69      0.67      0.68      1000\n",
+      "           8       0.73      0.73      0.73      1000\n",
+      "           9       0.64      0.69      0.66      1000\n",
+      "\n",
+      "    accuracy                           0.63     10000\n",
+      "   macro avg       0.63      0.63      0.63     10000\n",
+      "weighted avg       0.63      0.63      0.63     10000\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import classification_report\n",
+    "\n",
+    "# Obtain predictions on the test set\n",
+    "y_pred = model.predict(x_test)\n",
+    "y_pred_classes = y_pred.argmax(axis=1)\n",
+    "\n",
+    "# Generate a classification report\n",
+    "print(classification_report(y_test, y_pred_classes))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Visualization of the Confusion Matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import confusion_matrix\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Create the confusion matrix\n",
+    "confusion_mtx = confusion_matrix(y_test, y_pred_classes)\n",
+    "\n",
+    "# Plotting the confusion matrix\n",
+    "plt.figure(figsize=(10, 8))\n",
+    "sns.heatmap(confusion_mtx, annot=True, fmt='d', cmap='Blues')\n",
+    "plt.xlabel('Predicted Label')\n",
+    "plt.ylabel('True Label')\n",
+    "plt.title('Confusion Matrix')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Transfer Learning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_7\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1mModel: \"functional_7\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ input_layer_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_conv1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,792</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_conv2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">36,928</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_pool (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_conv1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_conv2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">147,584</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_pool (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">590,080</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">590,080</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_pool (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">1,180,160</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_pool (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │     <span style=\"color: #00af00; text-decoration-color: #00af00\">2,359,808</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_pool (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">262,656</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">131,328</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,570</span> │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ input_layer_1 (\u001b[38;5;33mInputLayer\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m3\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_conv1 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │         \u001b[38;5;34m1,792\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_conv2 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m36,928\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block1_pool (\u001b[38;5;33mMaxPooling2D\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_conv1 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_conv2 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │       \u001b[38;5;34m147,584\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block2_pool (\u001b[38;5;33mMaxPooling2D\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv1 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │       \u001b[38;5;34m295,168\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv2 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │       \u001b[38;5;34m590,080\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_conv3 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │       \u001b[38;5;34m590,080\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block3_pool (\u001b[38;5;33mMaxPooling2D\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv1 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m1,180,160\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv2 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m2,359,808\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_conv3 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m2,359,808\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block4_pool (\u001b[38;5;33mMaxPooling2D\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv1 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m2,359,808\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv2 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m2,359,808\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_conv3 (\u001b[38;5;33mConv2D\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │     \u001b[38;5;34m2,359,808\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ block5_pool (\u001b[38;5;33mMaxPooling2D\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │       \u001b[38;5;34m262,656\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │       \u001b[38;5;34m131,328\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_4 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m2,570\u001b[0m │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">15,111,242</span> (57.64 MB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m15,111,242\u001b[0m (57.64 MB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">396,554</span> (1.51 MB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m396,554\u001b[0m (1.51 MB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">14,714,688</span> (56.13 MB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m14,714,688\u001b[0m (56.13 MB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.applications import VGG16\n",
+    "from tensorflow.keras.models import Model\n",
+    "from tensorflow.keras.layers import Flatten, Dense, Dropout\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "\n",
+    "# Loading the pre-trained VGG16 model\n",
+    "base_model = VGG16(weights='imagenet', include_top=False, input_shape=(32, 32, 3))\n",
+    "\n",
+    "# Freeze the layers of the base model so that they are not trained.\n",
+    "for layer in base_model.layers:\n",
+    "    layer.trainable = False\n",
+    "\n",
+    "# Add custom layers to the model\n",
+    "x = Flatten()(base_model.output)\n",
+    "x = Dense(512, activation='relu')(x)\n",
+    "x = Dropout(0.5)(x)\n",
+    "x = Dense(256, activation='relu')(x)\n",
+    "x = Dropout(0.5)(x)\n",
+    "output = Dense(10, activation='softmax')(x)\n",
+    "\n",
+    "# Define the complete model\n",
+    "model = Model(inputs=base_model.input, outputs=output)\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(optimizer=Adam(learning_rate=0.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "# See the structure of the model\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m478s\u001b[0m 304ms/step - accuracy: 0.1872 - loss: 13.5271 - val_accuracy: 0.2114 - val_loss: 2.1875 - learning_rate: 1.0000e-04\n",
+      "Epoch 2/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m446s\u001b[0m 285ms/step - accuracy: 0.2132 - loss: 2.4738 - val_accuracy: 0.3177 - val_loss: 2.0388 - learning_rate: 1.0000e-04\n",
+      "Epoch 3/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m504s\u001b[0m 287ms/step - accuracy: 0.2727 - loss: 2.0863 - val_accuracy: 0.4113 - val_loss: 1.7796 - learning_rate: 1.0000e-04\n",
+      "Epoch 4/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m467s\u001b[0m 299ms/step - accuracy: 0.3390 - loss: 1.8680 - val_accuracy: 0.4708 - val_loss: 1.6096 - learning_rate: 1.0000e-04\n",
+      "Epoch 5/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m447s\u001b[0m 286ms/step - accuracy: 0.3827 - loss: 1.7453 - val_accuracy: 0.5083 - val_loss: 1.4940 - learning_rate: 1.0000e-04\n",
+      "Epoch 6/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m472s\u001b[0m 302ms/step - accuracy: 0.4212 - loss: 1.6380 - val_accuracy: 0.5290 - val_loss: 1.4268 - learning_rate: 1.0000e-04\n",
+      "Epoch 7/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m480s\u001b[0m 307ms/step - accuracy: 0.4554 - loss: 1.5599 - val_accuracy: 0.5499 - val_loss: 1.3700 - learning_rate: 1.0000e-04\n",
+      "Epoch 8/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m458s\u001b[0m 293ms/step - accuracy: 0.4827 - loss: 1.4785 - val_accuracy: 0.5633 - val_loss: 1.3192 - learning_rate: 1.0000e-04\n",
+      "Epoch 9/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m456s\u001b[0m 292ms/step - accuracy: 0.4988 - loss: 1.4336 - val_accuracy: 0.5769 - val_loss: 1.2906 - learning_rate: 1.0000e-04\n",
+      "Epoch 10/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m452s\u001b[0m 289ms/step - accuracy: 0.5215 - loss: 1.3873 - val_accuracy: 0.5908 - val_loss: 1.2560 - learning_rate: 1.0000e-04\n",
+      "Epoch 11/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m507s\u001b[0m 292ms/step - accuracy: 0.5415 - loss: 1.3309 - val_accuracy: 0.5950 - val_loss: 1.2286 - learning_rate: 1.0000e-04\n",
+      "Epoch 12/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m452s\u001b[0m 289ms/step - accuracy: 0.5478 - loss: 1.3076 - val_accuracy: 0.6020 - val_loss: 1.2051 - learning_rate: 1.0000e-04\n",
+      "Epoch 13/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m508s\u001b[0m 293ms/step - accuracy: 0.5551 - loss: 1.2787 - val_accuracy: 0.6072 - val_loss: 1.1885 - learning_rate: 1.0000e-04\n",
+      "Epoch 14/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m937s\u001b[0m 571ms/step - accuracy: 0.5676 - loss: 1.2442 - val_accuracy: 0.6096 - val_loss: 1.1775 - learning_rate: 1.0000e-04\n",
+      "Epoch 15/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m683s\u001b[0m 437ms/step - accuracy: 0.5818 - loss: 1.2069 - val_accuracy: 0.6135 - val_loss: 1.1651 - learning_rate: 1.0000e-04\n",
+      "Epoch 16/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m627s\u001b[0m 401ms/step - accuracy: 0.5853 - loss: 1.1943 - val_accuracy: 0.6167 - val_loss: 1.1522 - learning_rate: 1.0000e-04\n",
+      "Epoch 17/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m778s\u001b[0m 498ms/step - accuracy: 0.5969 - loss: 1.1604 - val_accuracy: 0.6247 - val_loss: 1.1401 - learning_rate: 1.0000e-04\n",
+      "Epoch 18/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m558s\u001b[0m 357ms/step - accuracy: 0.6033 - loss: 1.1344 - val_accuracy: 0.6242 - val_loss: 1.1311 - learning_rate: 1.0000e-04\n",
+      "Epoch 19/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m559s\u001b[0m 358ms/step - accuracy: 0.6140 - loss: 1.1181 - val_accuracy: 0.6290 - val_loss: 1.1214 - learning_rate: 1.0000e-04\n",
+      "Epoch 20/20\n",
+      "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m703s\u001b[0m 450ms/step - accuracy: 0.6167 - loss: 1.0921 - val_accuracy: 0.6325 - val_loss: 1.1089 - learning_rate: 1.0000e-04\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Training the model with Transfer Learning\n",
+    "history = model.fit(\n",
+    "    x_train, y_train,\n",
+    "    epochs=20,\n",
+    "    batch_size=32,\n",
+    "    validation_data=(x_test, y_test),\n",
+    "    callbacks=[early_stopping, reduce_lr]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "313/313 - 102s - 327ms/step - accuracy: 0.6325 - loss: 1.1089\n",
+      "Transfer Learning Model Accuracy: 0.6325\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluation of the transferred model\n",
+    "test_loss, test_accuracy = model.evaluate(x_test, y_test, verbose=2)\n",
+    "print(f\"Transfer Learning Model Accuracy: {test_accuracy:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Unfreezing the model and retraining again"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras.utils import to_categorical\n",
+    "\n",
+    "# Convert labels for one-hot encoding\n",
+    "y_train = to_categorical(y_train, 10)\n",
+    "y_test = to_categorical(y_test, 10)\n",
+    "\n",
+    "# Unfreeze all layers\n",
+    "for layer in model.layers:\n",
+    "    layer.trainable = True\n",
+    "\n",
+    "# Recompile the template\n",
+    "model.compile(optimizer='adam', \n",
+    "              loss='categorical_crossentropy', \n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "# Training the model\n",
+    "history = model.fit(\n",
+    "    x_train, \n",
+    "    y_train, \n",
+    "    epochs=5, \n",
+    "    validation_data=(x_test, y_test)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
+     ]
+    }
+   ],
+   "source": [
+    "# Save the best model\n",
+    "model.save('best_model.h5')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved images to test_images\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from PIL import Image\n",
+    "from tensorflow.keras.datasets import cifar10\n",
+    "\n",
+    "# Load CIFAR-10 data\n",
+    "(x_train, y_train), (x_test, y_test) = cifar10.load_data()\n",
+    "\n",
+    "# Create a directory to save images\n",
+    "output_dir = 'test_images'\n",
+    "os.makedirs(output_dir, exist_ok=True)\n",
+    "\n",
+    "# Extract a small subset of images (e.g., 5 images) from x_test\n",
+    "subset_size = 5\n",
+    "x_test_subset = x_test[:subset_size]\n",
+    "\n",
+    "# Save each image in the output directory\n",
+    "for i, img in enumerate(x_test_subset):\n",
+    "    img_pil = Image.fromarray(img)\n",
+    "    img_path = os.path.join(output_dir, f'test_image_{i+1}.png')\n",
+    "    img_pil.save(img_path)\n",
+    "\n",
+    "print(f\"Saved images to {output_dir}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/test_images/test_image_1.png b/test_images/test_image_1.png
new file mode 100644
index 00000000..d0a8b7d2
Binary files /dev/null and b/test_images/test_image_1.png differ
diff --git a/test_images/test_image_2.png b/test_images/test_image_2.png
new file mode 100644
index 00000000..fac03a26
Binary files /dev/null and b/test_images/test_image_2.png differ
diff --git a/test_images/test_image_3.png b/test_images/test_image_3.png
new file mode 100644
index 00000000..d26838b1
Binary files /dev/null and b/test_images/test_image_3.png differ
diff --git a/test_images/test_image_4.png b/test_images/test_image_4.png
new file mode 100644
index 00000000..7e6e5bf1
Binary files /dev/null and b/test_images/test_image_4.png differ
diff --git a/test_images/test_image_5.png b/test_images/test_image_5.png
new file mode 100644
index 00000000..7528fad4
Binary files /dev/null and b/test_images/test_image_5.png differ
diff --git a/training_history.pkl b/training_history.pkl
new file mode 100644
index 00000000..13414d41
Binary files /dev/null and b/training_history.pkl differ