08_b-neural_networks.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-09-12 19:11:45.544389: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:45.544413: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>\n",
       "\n",
       "    @import url('http://fonts.googleapis.com/css?family=Source+Code+Pro');\n",
       "\n",
       "    @import url('http://fonts.googleapis.com/css?family=Kameron');\n",
       "    @import url('http://fonts.googleapis.com/css?family=Crimson+Text');\n",
       "\n",
       "    @import url('http://fonts.googleapis.com/css?family=Lato');\n",
       "    @import url('http://fonts.googleapis.com/css?family=Source+Sans+Pro');\n",
       "\n",
       "    @import url('http://fonts.googleapis.com/css?family=Lora');\n",
       "\n",
       "\n",
       "    body {\n",
       "        font-family: 'Lora', Consolas, sans-serif;\n",
       "\n",
       "        -webkit-print-color-adjust: exact important !;\n",
       "\n",
       "\n",
       "\n",
       "    }\n",
       "\n",
       "    .alert-block {\n",
       "        width: 95%;\n",
       "        margin: auto;\n",
       "    }\n",
       "\n",
       "    .rendered_html code\n",
       "    {\n",
       "        color: black;\n",
       "        background: #eaf0ff;\n",
       "        background: #f5f5f5;\n",
       "        padding: 1pt;\n",
       "        font-family:  'Source Code Pro', Consolas, monocco, monospace;\n",
       "    }\n",
       "\n",
       "    p {\n",
       "      line-height: 140%;\n",
       "    }\n",
       "\n",
       "    strong code {\n",
       "        background: red;\n",
       "    }\n",
       "\n",
       "    .rendered_html strong code\n",
       "    {\n",
       "        background: #f5f5f5;\n",
       "    }\n",
       "\n",
       "    .CodeMirror pre {\n",
       "    font-family: 'Source Code Pro', monocco, Consolas, monocco, monospace;\n",
       "    }\n",
       "\n",
       "    .cm-s-ipython span.cm-keyword {\n",
       "        font-weight: normal;\n",
       "     }\n",
       "\n",
       "     strong {\n",
       "         background: #f5f5f5;\n",
       "         margin-top: 4pt;\n",
       "         margin-bottom: 4pt;\n",
       "         padding: 2pt;\n",
       "         border: 0.5px solid #a0a0a0;\n",
       "         font-weight: bold;\n",
       "         color: darkred;\n",
       "     }\n",
       "\n",
       "\n",
       "    div #notebook {\n",
       "        # font-size: 10pt;\n",
       "        line-height: 145%;\n",
       "        }\n",
       "\n",
       "    li {\n",
       "        line-height: 145%;\n",
       "    }\n",
       "\n",
       "    div.output_area pre {\n",
       "        background: #fff9d8 !important;\n",
       "        padding: 5pt;\n",
       "\n",
       "       -webkit-print-color-adjust: exact;\n",
       "\n",
       "    }\n",
       "\n",
       "\n",
       "\n",
       "    h1, h2, h3, h4 {\n",
       "        font-family: Kameron, arial;\n",
       "\n",
       "    }\n",
       "\n",
       "    div#maintoolbar {display: none !important;}\n",
       "    /*\n",
       "\n",
       "    div#site {\n",
       "        border-top: 20px solid #1F407A;\n",
       "        border-right: 20px solid #1F407A;\n",
       "        margin-bottom: 0;\n",
       "        padding-bottom: 0;\n",
       "    }\n",
       "    div#toc-wrapper {\n",
       "        border-left: 20px solid #1F407A;\n",
       "        border-top: 20px solid #1F407A;\n",
       "\n",
       "    }\n",
       "\n",
       "    body {\n",
       "        margin-botton:10px;\n",
       "    }\n",
       "    */\n",
       "\n",
       "</style>\n",
       "    <script>\n",
       "IPython.OutputArea.prototype._should_scroll = function(lines) {\n",
       "        return false;\n",
       "}\n",
       "    </script>\n",
       "\n",
       "\n",
       "<footer id=\"attribution\" style=\"float:left; color:#1F407A; background:#fff; font-family: helvetica;\">\n",
       "    Copyright (C) 2019-2021 Scientific IT Services of ETH Zurich,\n",
       "    <p>\n",
       "    Contributing Authors:\n",
       "    Dr. Tarun Chadha,\n",
       "    Dr. Franziska Oschmann,\n",
       "    Dr. Mikolaj Rybinski,\n",
       "    Dr. Uwe Schmitt.\n",
       "    </p<\n",
       "</footer>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# IGNORE THIS CELL WHICH CUSTOMIZES LAYOUT AND STYLING OF THE NOTEBOOK !\n",
    "from numpy.random import seed\n",
    "\n",
    "seed(42)\n",
    "import tensorflow as tf\n",
    "\n",
    "tf.random.set_seed(46)\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "sns.set(style=\"darkgrid\")\n",
    "mpl.rcParams[\"lines.linewidth\"] = 3\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "%config IPCompleter.greedy=True\n",
    "import warnings\n",
    "\n",
    "warnings.filterwarnings(\"ignore\", category=FutureWarning)\n",
    "from IPython.core.display import HTML\n",
    "\n",
    "HTML(open(\"custom.html\", \"r\").read())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Chapter 8b: Introduction to Tensorflow"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Introduction to TensorFlow (keras API)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### A bit about Keras?\n",
    "\n",
    "* It is a high level API to create and work with neural networks\n",
    "* Used to support multiple backends such as **TensorFlow** from Google, **Theano** (Theano is dead now) and **CNTK** (Microsoft Cognitive Toolkit), up till release 2.3.0 \n",
    "* Very good for creating neural nets quickly and hides away a lot of tedious work\n",
    "* Has been incorporated into official TensorFlow (which obviously only works with tensorflow) and is its main API as of version 2.0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<center>\n",
    "<figure>\n",
    "<img src=\"./images/neuralnets/neural_net_keras_1.svg\" width=\"700\"/>\n",
    "<figcaption>Building this model in TensorFlow (Keras)</figcaption>\n",
    "</figure>\n",
    "</center>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " dense (Dense)               (None, 4)                 12        \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 4)                 20        \n",
      "                                                                 \n",
      " dense_2 (Dense)             (None, 1)                 5         \n",
      "                                                                 \n",
      " activation (Activation)     (None, 1)                 0         \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 37\n",
      "Trainable params: 37\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-09-12 19:11:47.605524: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:975] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
      "2022-09-12 19:11:47.605838: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.605896: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublas.so.11'; dlerror: libcublas.so.11: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.605951: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublasLt.so.11'; dlerror: libcublasLt.so.11: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606005: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcufft.so.10'; dlerror: libcufft.so.10: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606059: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcurand.so.10'; dlerror: libcurand.so.10: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606113: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606165: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusparse.so.11'; dlerror: libcusparse.so.11: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606219: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory\n",
      "2022-09-12 19:11:47.606226: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1850] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
      "Skipping registering GPU devices...\n",
      "2022-09-12 19:11:47.606583: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "# Say hello to Tensorflow\n",
    "from tensorflow.keras.layers import Activation, Dense\n",
    "from tensorflow.keras.models import Sequential\n",
    "\n",
    "# Creating a model\n",
    "model = Sequential()\n",
    "\n",
    "# Adding layers to this model\n",
    "# 1st Hidden layer\n",
    "# A Dense/fully-connected layer which takes as input a\n",
    "# feature array of shape (samples, num_features)\n",
    "# Here input_shape = (2,) means that the layer expects an input with num_features = 2\n",
    "# and the sample size could be anything\n",
    "# The activation function for this layer is set to \"relu\"\n",
    "model.add(Dense(units=4, input_shape=(2,), activation=\"relu\"))\n",
    "\n",
    "# 2nd Hidden layer\n",
    "# This is also a fully-connected layer and we do not need to specify the\n",
    "# shape of the input anymore (We need to do that only for the first layer)\n",
    "# NOTE: Now we didn't add the activation seperately. Instead we just added it\n",
    "# while calling Dense(). This and the way used for the first layer are Equivalent!\n",
    "model.add(Dense(units=4, activation=\"relu\"))\n",
    "\n",
    "\n",
    "# The output layer\n",
    "model.add(Dense(units=1))\n",
    "model.add(Activation(\"sigmoid\"))\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### XOR using neural networks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import train_test_split\n",
    "from tensorflow.keras.layers import Dense\n",
    "from tensorflow.keras.models import Sequential"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 321,
       "width": 338
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Creating a network to solve the XOR problem\n",
    "\n",
    "# Loading and plotting the data\n",
    "xor = pd.read_csv(\"data/xor.csv\")\n",
    "\n",
    "# Using x and y coordinates as featues\n",
    "features = xor.iloc[:, :-1]\n",
    "# Convert boolean to integer values (True->1 and False->0)\n",
    "labels = 1 - xor.iloc[:, -1].astype(int)\n",
    "\n",
    "colors = [[\"steelblue\", \"chocolate\"][i] for i in labels]\n",
    "plt.figure(figsize=(5, 5))\n",
    "plt.xlim([-2, 2])\n",
    "plt.ylim([-2, 2])\n",
    "plt.title(\"Blue points are False\")\n",
    "plt.scatter(features[\"x\"], features[\"y\"], color=colors, marker=\"o\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Building a simple Tensorflow model\n",
    "\n",
    "\n",
    "def a_simple_NN():\n",
    "\n",
    "    model = Sequential()\n",
    "\n",
    "    model.add(Dense(4, input_shape=(2,), activation=\"relu\"))\n",
    "\n",
    "    model.add(Dense(4, activation=\"relu\"))\n",
    "\n",
    "    model.add(Dense(1, activation=\"sigmoid\"))\n",
    "\n",
    "    model.compile(loss=\"binary_crossentropy\", optimizer=\"rmsprop\", metrics=[\"accuracy\"])\n",
    "\n",
    "    return model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/300\n",
      "11/11 [==============================] - 1s 13ms/step - loss: 0.8279 - accuracy: 0.4086 - val_loss: 0.8232 - val_accuracy: 0.3933\n",
      "Epoch 2/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.8065 - accuracy: 0.4086 - val_loss: 0.8063 - val_accuracy: 0.4067\n",
      "Epoch 3/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7915 - accuracy: 0.4371 - val_loss: 0.7915 - val_accuracy: 0.4067\n",
      "Epoch 4/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7782 - accuracy: 0.4400 - val_loss: 0.7789 - val_accuracy: 0.4000\n",
      "Epoch 5/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7666 - accuracy: 0.4543 - val_loss: 0.7671 - val_accuracy: 0.4267\n",
      "Epoch 6/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7561 - accuracy: 0.4457 - val_loss: 0.7568 - val_accuracy: 0.4267\n",
      "Epoch 7/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7465 - accuracy: 0.4371 - val_loss: 0.7470 - val_accuracy: 0.4133\n",
      "Epoch 8/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7378 - accuracy: 0.4314 - val_loss: 0.7383 - val_accuracy: 0.4133\n",
      "Epoch 9/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7297 - accuracy: 0.4286 - val_loss: 0.7301 - val_accuracy: 0.4067\n",
      "Epoch 10/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7224 - accuracy: 0.4286 - val_loss: 0.7227 - val_accuracy: 0.4067\n",
      "Epoch 11/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7160 - accuracy: 0.4371 - val_loss: 0.7163 - val_accuracy: 0.4067\n",
      "Epoch 12/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7100 - accuracy: 0.4314 - val_loss: 0.7102 - val_accuracy: 0.4067\n",
      "Epoch 13/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.7045 - accuracy: 0.4400 - val_loss: 0.7048 - val_accuracy: 0.4000\n",
      "Epoch 14/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6995 - accuracy: 0.4457 - val_loss: 0.6996 - val_accuracy: 0.4667\n",
      "Epoch 15/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6950 - accuracy: 0.4886 - val_loss: 0.6950 - val_accuracy: 0.4933\n",
      "Epoch 16/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6907 - accuracy: 0.5314 - val_loss: 0.6904 - val_accuracy: 0.5400\n",
      "Epoch 17/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6866 - accuracy: 0.6057 - val_loss: 0.6859 - val_accuracy: 0.6200\n",
      "Epoch 18/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6825 - accuracy: 0.6229 - val_loss: 0.6814 - val_accuracy: 0.6267\n",
      "Epoch 19/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6783 - accuracy: 0.6171 - val_loss: 0.6765 - val_accuracy: 0.6267\n",
      "Epoch 20/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6739 - accuracy: 0.6314 - val_loss: 0.6715 - val_accuracy: 0.6533\n",
      "Epoch 21/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6691 - accuracy: 0.6486 - val_loss: 0.6674 - val_accuracy: 0.6533\n",
      "Epoch 22/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6654 - accuracy: 0.6571 - val_loss: 0.6637 - val_accuracy: 0.6533\n",
      "Epoch 23/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6622 - accuracy: 0.6657 - val_loss: 0.6604 - val_accuracy: 0.6600\n",
      "Epoch 24/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6588 - accuracy: 0.6686 - val_loss: 0.6573 - val_accuracy: 0.6667\n",
      "Epoch 25/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6557 - accuracy: 0.6686 - val_loss: 0.6539 - val_accuracy: 0.6667\n",
      "Epoch 26/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6525 - accuracy: 0.6714 - val_loss: 0.6506 - val_accuracy: 0.6733\n",
      "Epoch 27/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6487 - accuracy: 0.6771 - val_loss: 0.6467 - val_accuracy: 0.6733\n",
      "Epoch 28/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6435 - accuracy: 0.7029 - val_loss: 0.6413 - val_accuracy: 0.6933\n",
      "Epoch 29/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6359 - accuracy: 0.7286 - val_loss: 0.6345 - val_accuracy: 0.7133\n",
      "Epoch 30/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6279 - accuracy: 0.7514 - val_loss: 0.6272 - val_accuracy: 0.7200\n",
      "Epoch 31/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6190 - accuracy: 0.7771 - val_loss: 0.6189 - val_accuracy: 0.7467\n",
      "Epoch 32/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.6095 - accuracy: 0.7771 - val_loss: 0.6100 - val_accuracy: 0.7733\n",
      "Epoch 33/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5997 - accuracy: 0.8029 - val_loss: 0.6010 - val_accuracy: 0.7733\n",
      "Epoch 34/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5901 - accuracy: 0.8171 - val_loss: 0.5921 - val_accuracy: 0.7933\n",
      "Epoch 35/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5809 - accuracy: 0.8257 - val_loss: 0.5838 - val_accuracy: 0.8000\n",
      "Epoch 36/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5719 - accuracy: 0.8286 - val_loss: 0.5754 - val_accuracy: 0.8200\n",
      "Epoch 37/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5632 - accuracy: 0.8343 - val_loss: 0.5677 - val_accuracy: 0.8267\n",
      "Epoch 38/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5547 - accuracy: 0.8571 - val_loss: 0.5605 - val_accuracy: 0.8400\n",
      "Epoch 39/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5470 - accuracy: 0.8486 - val_loss: 0.5534 - val_accuracy: 0.8467\n",
      "Epoch 40/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5394 - accuracy: 0.8600 - val_loss: 0.5464 - val_accuracy: 0.8600\n",
      "Epoch 41/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5324 - accuracy: 0.8629 - val_loss: 0.5394 - val_accuracy: 0.8600\n",
      "Epoch 42/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5251 - accuracy: 0.8714 - val_loss: 0.5325 - val_accuracy: 0.8600\n",
      "Epoch 43/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5179 - accuracy: 0.8743 - val_loss: 0.5257 - val_accuracy: 0.8600\n",
      "Epoch 44/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5107 - accuracy: 0.8657 - val_loss: 0.5190 - val_accuracy: 0.8600\n",
      "Epoch 45/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.5038 - accuracy: 0.8686 - val_loss: 0.5125 - val_accuracy: 0.8667\n",
      "Epoch 46/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4969 - accuracy: 0.8743 - val_loss: 0.5059 - val_accuracy: 0.8667\n",
      "Epoch 47/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4904 - accuracy: 0.8714 - val_loss: 0.4999 - val_accuracy: 0.8667\n",
      "Epoch 48/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4838 - accuracy: 0.8743 - val_loss: 0.4935 - val_accuracy: 0.8667\n",
      "Epoch 49/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4774 - accuracy: 0.8743 - val_loss: 0.4873 - val_accuracy: 0.8667\n",
      "Epoch 50/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4711 - accuracy: 0.8743 - val_loss: 0.4813 - val_accuracy: 0.8600\n",
      "Epoch 51/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4650 - accuracy: 0.8743 - val_loss: 0.4754 - val_accuracy: 0.8600\n",
      "Epoch 52/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4591 - accuracy: 0.8743 - val_loss: 0.4699 - val_accuracy: 0.8600\n",
      "Epoch 53/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4532 - accuracy: 0.8800 - val_loss: 0.4643 - val_accuracy: 0.8600\n",
      "Epoch 54/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4476 - accuracy: 0.8829 - val_loss: 0.4590 - val_accuracy: 0.8600\n",
      "Epoch 55/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4422 - accuracy: 0.8829 - val_loss: 0.4539 - val_accuracy: 0.8600\n",
      "Epoch 56/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4368 - accuracy: 0.8829 - val_loss: 0.4490 - val_accuracy: 0.8667\n",
      "Epoch 57/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4317 - accuracy: 0.8800 - val_loss: 0.4440 - val_accuracy: 0.8667\n",
      "Epoch 58/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4264 - accuracy: 0.8857 - val_loss: 0.4389 - val_accuracy: 0.8667\n",
      "Epoch 59/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4211 - accuracy: 0.8857 - val_loss: 0.4339 - val_accuracy: 0.8667\n",
      "Epoch 60/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4159 - accuracy: 0.8857 - val_loss: 0.4292 - val_accuracy: 0.8667\n",
      "Epoch 61/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4110 - accuracy: 0.8914 - val_loss: 0.4243 - val_accuracy: 0.8667\n",
      "Epoch 62/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4058 - accuracy: 0.8886 - val_loss: 0.4192 - val_accuracy: 0.8667\n",
      "Epoch 63/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.4007 - accuracy: 0.8886 - val_loss: 0.4141 - val_accuracy: 0.8667\n",
      "Epoch 64/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3954 - accuracy: 0.8943 - val_loss: 0.4092 - val_accuracy: 0.8667\n",
      "Epoch 65/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3902 - accuracy: 0.8943 - val_loss: 0.4043 - val_accuracy: 0.8667\n",
      "Epoch 66/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3849 - accuracy: 0.8914 - val_loss: 0.3992 - val_accuracy: 0.8667\n",
      "Epoch 67/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3798 - accuracy: 0.9000 - val_loss: 0.3945 - val_accuracy: 0.8667\n",
      "Epoch 68/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3750 - accuracy: 0.9029 - val_loss: 0.3900 - val_accuracy: 0.8800\n",
      "Epoch 69/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3703 - accuracy: 0.9000 - val_loss: 0.3853 - val_accuracy: 0.8733\n",
      "Epoch 70/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3655 - accuracy: 0.9029 - val_loss: 0.3804 - val_accuracy: 0.8800\n",
      "Epoch 71/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3607 - accuracy: 0.9086 - val_loss: 0.3755 - val_accuracy: 0.8867\n",
      "Epoch 72/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3559 - accuracy: 0.9086 - val_loss: 0.3712 - val_accuracy: 0.8867\n",
      "Epoch 73/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3512 - accuracy: 0.9086 - val_loss: 0.3665 - val_accuracy: 0.8933\n",
      "Epoch 74/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3468 - accuracy: 0.9143 - val_loss: 0.3623 - val_accuracy: 0.8933\n",
      "Epoch 75/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3425 - accuracy: 0.9143 - val_loss: 0.3580 - val_accuracy: 0.9000\n",
      "Epoch 76/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3386 - accuracy: 0.9143 - val_loss: 0.3541 - val_accuracy: 0.9000\n",
      "Epoch 77/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3345 - accuracy: 0.9143 - val_loss: 0.3499 - val_accuracy: 0.9000\n",
      "Epoch 78/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3305 - accuracy: 0.9171 - val_loss: 0.3462 - val_accuracy: 0.9000\n",
      "Epoch 79/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3267 - accuracy: 0.9171 - val_loss: 0.3422 - val_accuracy: 0.9000\n",
      "Epoch 80/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3225 - accuracy: 0.9171 - val_loss: 0.3380 - val_accuracy: 0.9000\n",
      "Epoch 81/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3186 - accuracy: 0.9229 - val_loss: 0.3339 - val_accuracy: 0.9000\n",
      "Epoch 82/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3145 - accuracy: 0.9229 - val_loss: 0.3295 - val_accuracy: 0.9000\n",
      "Epoch 83/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3108 - accuracy: 0.9229 - val_loss: 0.3254 - val_accuracy: 0.9000\n",
      "Epoch 84/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3066 - accuracy: 0.9257 - val_loss: 0.3215 - val_accuracy: 0.9000\n",
      "Epoch 85/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.3028 - accuracy: 0.9286 - val_loss: 0.3177 - val_accuracy: 0.9067\n",
      "Epoch 86/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2989 - accuracy: 0.9286 - val_loss: 0.3135 - val_accuracy: 0.9133\n",
      "Epoch 87/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2954 - accuracy: 0.9286 - val_loss: 0.3099 - val_accuracy: 0.9133\n",
      "Epoch 88/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2918 - accuracy: 0.9286 - val_loss: 0.3066 - val_accuracy: 0.9133\n",
      "Epoch 89/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2885 - accuracy: 0.9257 - val_loss: 0.3034 - val_accuracy: 0.9133\n",
      "Epoch 90/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2852 - accuracy: 0.9286 - val_loss: 0.3003 - val_accuracy: 0.9133\n",
      "Epoch 91/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2819 - accuracy: 0.9257 - val_loss: 0.2971 - val_accuracy: 0.9133\n",
      "Epoch 92/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2787 - accuracy: 0.9257 - val_loss: 0.2942 - val_accuracy: 0.9133\n",
      "Epoch 93/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2754 - accuracy: 0.9257 - val_loss: 0.2907 - val_accuracy: 0.9133\n",
      "Epoch 94/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2722 - accuracy: 0.9286 - val_loss: 0.2875 - val_accuracy: 0.9267\n",
      "Epoch 95/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2688 - accuracy: 0.9314 - val_loss: 0.2843 - val_accuracy: 0.9333\n",
      "Epoch 96/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2658 - accuracy: 0.9286 - val_loss: 0.2813 - val_accuracy: 0.9333\n",
      "Epoch 97/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2625 - accuracy: 0.9314 - val_loss: 0.2786 - val_accuracy: 0.9333\n",
      "Epoch 98/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2595 - accuracy: 0.9314 - val_loss: 0.2756 - val_accuracy: 0.9333\n",
      "Epoch 99/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2562 - accuracy: 0.9343 - val_loss: 0.2728 - val_accuracy: 0.9333\n",
      "Epoch 100/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2531 - accuracy: 0.9371 - val_loss: 0.2703 - val_accuracy: 0.9333\n",
      "Epoch 101/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2505 - accuracy: 0.9343 - val_loss: 0.2677 - val_accuracy: 0.9400\n",
      "Epoch 102/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2475 - accuracy: 0.9343 - val_loss: 0.2650 - val_accuracy: 0.9467\n",
      "Epoch 103/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2444 - accuracy: 0.9314 - val_loss: 0.2622 - val_accuracy: 0.9533\n",
      "Epoch 104/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2417 - accuracy: 0.9371 - val_loss: 0.2597 - val_accuracy: 0.9533\n",
      "Epoch 105/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2388 - accuracy: 0.9343 - val_loss: 0.2574 - val_accuracy: 0.9533\n",
      "Epoch 106/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2364 - accuracy: 0.9371 - val_loss: 0.2552 - val_accuracy: 0.9533\n",
      "Epoch 107/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2336 - accuracy: 0.9371 - val_loss: 0.2530 - val_accuracy: 0.9533\n",
      "Epoch 108/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2311 - accuracy: 0.9429 - val_loss: 0.2506 - val_accuracy: 0.9533\n",
      "Epoch 109/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2287 - accuracy: 0.9429 - val_loss: 0.2480 - val_accuracy: 0.9533\n",
      "Epoch 110/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2261 - accuracy: 0.9429 - val_loss: 0.2455 - val_accuracy: 0.9533\n",
      "Epoch 111/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2237 - accuracy: 0.9429 - val_loss: 0.2433 - val_accuracy: 0.9533\n",
      "Epoch 112/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2211 - accuracy: 0.9429 - val_loss: 0.2411 - val_accuracy: 0.9533\n",
      "Epoch 113/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2188 - accuracy: 0.9429 - val_loss: 0.2394 - val_accuracy: 0.9467\n",
      "Epoch 114/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2164 - accuracy: 0.9429 - val_loss: 0.2371 - val_accuracy: 0.9467\n",
      "Epoch 115/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2144 - accuracy: 0.9400 - val_loss: 0.2356 - val_accuracy: 0.9467\n",
      "Epoch 116/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2125 - accuracy: 0.9429 - val_loss: 0.2336 - val_accuracy: 0.9467\n",
      "Epoch 117/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2106 - accuracy: 0.9400 - val_loss: 0.2318 - val_accuracy: 0.9467\n",
      "Epoch 118/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2084 - accuracy: 0.9429 - val_loss: 0.2299 - val_accuracy: 0.9467\n",
      "Epoch 119/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2064 - accuracy: 0.9457 - val_loss: 0.2281 - val_accuracy: 0.9467\n",
      "Epoch 120/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2041 - accuracy: 0.9486 - val_loss: 0.2261 - val_accuracy: 0.9467\n",
      "Epoch 121/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2022 - accuracy: 0.9457 - val_loss: 0.2239 - val_accuracy: 0.9467\n",
      "Epoch 122/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.2003 - accuracy: 0.9486 - val_loss: 0.2226 - val_accuracy: 0.9467\n",
      "Epoch 123/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1982 - accuracy: 0.9543 - val_loss: 0.2209 - val_accuracy: 0.9467\n",
      "Epoch 124/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1964 - accuracy: 0.9543 - val_loss: 0.2193 - val_accuracy: 0.9467\n",
      "Epoch 125/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1946 - accuracy: 0.9600 - val_loss: 0.2178 - val_accuracy: 0.9467\n",
      "Epoch 126/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1931 - accuracy: 0.9571 - val_loss: 0.2163 - val_accuracy: 0.9467\n",
      "Epoch 127/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1911 - accuracy: 0.9571 - val_loss: 0.2152 - val_accuracy: 0.9533\n",
      "Epoch 128/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1898 - accuracy: 0.9571 - val_loss: 0.2136 - val_accuracy: 0.9533\n",
      "Epoch 129/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1881 - accuracy: 0.9571 - val_loss: 0.2117 - val_accuracy: 0.9533\n",
      "Epoch 130/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1865 - accuracy: 0.9571 - val_loss: 0.2099 - val_accuracy: 0.9533\n",
      "Epoch 131/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1846 - accuracy: 0.9571 - val_loss: 0.2084 - val_accuracy: 0.9533\n",
      "Epoch 132/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1830 - accuracy: 0.9571 - val_loss: 0.2067 - val_accuracy: 0.9600\n",
      "Epoch 133/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1814 - accuracy: 0.9571 - val_loss: 0.2052 - val_accuracy: 0.9600\n",
      "Epoch 134/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1799 - accuracy: 0.9571 - val_loss: 0.2042 - val_accuracy: 0.9600\n",
      "Epoch 135/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1781 - accuracy: 0.9571 - val_loss: 0.2029 - val_accuracy: 0.9600\n",
      "Epoch 136/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1767 - accuracy: 0.9571 - val_loss: 0.2017 - val_accuracy: 0.9533\n",
      "Epoch 137/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1752 - accuracy: 0.9571 - val_loss: 0.2001 - val_accuracy: 0.9600\n",
      "Epoch 138/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1740 - accuracy: 0.9571 - val_loss: 0.1990 - val_accuracy: 0.9533\n",
      "Epoch 139/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1726 - accuracy: 0.9571 - val_loss: 0.1974 - val_accuracy: 0.9600\n",
      "Epoch 140/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1712 - accuracy: 0.9571 - val_loss: 0.1963 - val_accuracy: 0.9600\n",
      "Epoch 141/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1699 - accuracy: 0.9571 - val_loss: 0.1947 - val_accuracy: 0.9600\n",
      "Epoch 142/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1684 - accuracy: 0.9600 - val_loss: 0.1929 - val_accuracy: 0.9600\n",
      "Epoch 143/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1672 - accuracy: 0.9571 - val_loss: 0.1916 - val_accuracy: 0.9600\n",
      "Epoch 144/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1658 - accuracy: 0.9600 - val_loss: 0.1904 - val_accuracy: 0.9600\n",
      "Epoch 145/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1646 - accuracy: 0.9600 - val_loss: 0.1891 - val_accuracy: 0.9600\n",
      "Epoch 146/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1633 - accuracy: 0.9600 - val_loss: 0.1882 - val_accuracy: 0.9600\n",
      "Epoch 147/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1620 - accuracy: 0.9600 - val_loss: 0.1871 - val_accuracy: 0.9600\n",
      "Epoch 148/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1608 - accuracy: 0.9600 - val_loss: 0.1859 - val_accuracy: 0.9600\n",
      "Epoch 149/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1598 - accuracy: 0.9600 - val_loss: 0.1849 - val_accuracy: 0.9600\n",
      "Epoch 150/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1587 - accuracy: 0.9600 - val_loss: 0.1837 - val_accuracy: 0.9600\n",
      "Epoch 151/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1575 - accuracy: 0.9600 - val_loss: 0.1829 - val_accuracy: 0.9600\n",
      "Epoch 152/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1565 - accuracy: 0.9600 - val_loss: 0.1818 - val_accuracy: 0.9600\n",
      "Epoch 153/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1554 - accuracy: 0.9600 - val_loss: 0.1806 - val_accuracy: 0.9600\n",
      "Epoch 154/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1543 - accuracy: 0.9600 - val_loss: 0.1793 - val_accuracy: 0.9600\n",
      "Epoch 155/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1532 - accuracy: 0.9600 - val_loss: 0.1781 - val_accuracy: 0.9600\n",
      "Epoch 156/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1526 - accuracy: 0.9571 - val_loss: 0.1772 - val_accuracy: 0.9600\n",
      "Epoch 157/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1513 - accuracy: 0.9600 - val_loss: 0.1761 - val_accuracy: 0.9600\n",
      "Epoch 158/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1505 - accuracy: 0.9600 - val_loss: 0.1753 - val_accuracy: 0.9600\n",
      "Epoch 159/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1496 - accuracy: 0.9600 - val_loss: 0.1744 - val_accuracy: 0.9600\n",
      "Epoch 160/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1490 - accuracy: 0.9600 - val_loss: 0.1736 - val_accuracy: 0.9600\n",
      "Epoch 161/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1479 - accuracy: 0.9600 - val_loss: 0.1724 - val_accuracy: 0.9600\n",
      "Epoch 162/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1469 - accuracy: 0.9600 - val_loss: 0.1718 - val_accuracy: 0.9600\n",
      "Epoch 163/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1462 - accuracy: 0.9600 - val_loss: 0.1708 - val_accuracy: 0.9600\n",
      "Epoch 164/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1450 - accuracy: 0.9600 - val_loss: 0.1696 - val_accuracy: 0.9600\n",
      "Epoch 165/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1442 - accuracy: 0.9600 - val_loss: 0.1683 - val_accuracy: 0.9600\n",
      "Epoch 166/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1434 - accuracy: 0.9600 - val_loss: 0.1675 - val_accuracy: 0.9600\n",
      "Epoch 167/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1425 - accuracy: 0.9600 - val_loss: 0.1670 - val_accuracy: 0.9600\n",
      "Epoch 168/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1417 - accuracy: 0.9600 - val_loss: 0.1661 - val_accuracy: 0.9600\n",
      "Epoch 169/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1411 - accuracy: 0.9629 - val_loss: 0.1652 - val_accuracy: 0.9600\n",
      "Epoch 170/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1403 - accuracy: 0.9600 - val_loss: 0.1646 - val_accuracy: 0.9600\n",
      "Epoch 171/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1393 - accuracy: 0.9629 - val_loss: 0.1639 - val_accuracy: 0.9600\n",
      "Epoch 172/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1387 - accuracy: 0.9600 - val_loss: 0.1628 - val_accuracy: 0.9600\n",
      "Epoch 173/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1380 - accuracy: 0.9600 - val_loss: 0.1620 - val_accuracy: 0.9600\n",
      "Epoch 174/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1371 - accuracy: 0.9629 - val_loss: 0.1613 - val_accuracy: 0.9600\n",
      "Epoch 175/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1363 - accuracy: 0.9600 - val_loss: 0.1608 - val_accuracy: 0.9600\n",
      "Epoch 176/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1359 - accuracy: 0.9657 - val_loss: 0.1599 - val_accuracy: 0.9600\n",
      "Epoch 177/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1350 - accuracy: 0.9657 - val_loss: 0.1588 - val_accuracy: 0.9600\n",
      "Epoch 178/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1343 - accuracy: 0.9600 - val_loss: 0.1580 - val_accuracy: 0.9600\n",
      "Epoch 179/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1337 - accuracy: 0.9657 - val_loss: 0.1572 - val_accuracy: 0.9600\n",
      "Epoch 180/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1329 - accuracy: 0.9600 - val_loss: 0.1567 - val_accuracy: 0.9600\n",
      "Epoch 181/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1323 - accuracy: 0.9629 - val_loss: 0.1561 - val_accuracy: 0.9600\n",
      "Epoch 182/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1317 - accuracy: 0.9629 - val_loss: 0.1553 - val_accuracy: 0.9600\n",
      "Epoch 183/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1309 - accuracy: 0.9657 - val_loss: 0.1542 - val_accuracy: 0.9600\n",
      "Epoch 184/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1305 - accuracy: 0.9657 - val_loss: 0.1537 - val_accuracy: 0.9600\n",
      "Epoch 185/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1297 - accuracy: 0.9657 - val_loss: 0.1532 - val_accuracy: 0.9600\n",
      "Epoch 186/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1291 - accuracy: 0.9657 - val_loss: 0.1523 - val_accuracy: 0.9600\n",
      "Epoch 187/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1286 - accuracy: 0.9686 - val_loss: 0.1514 - val_accuracy: 0.9600\n",
      "Epoch 188/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1278 - accuracy: 0.9686 - val_loss: 0.1507 - val_accuracy: 0.9600\n",
      "Epoch 189/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1270 - accuracy: 0.9629 - val_loss: 0.1503 - val_accuracy: 0.9600\n",
      "Epoch 190/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1267 - accuracy: 0.9686 - val_loss: 0.1495 - val_accuracy: 0.9600\n",
      "Epoch 191/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1261 - accuracy: 0.9657 - val_loss: 0.1487 - val_accuracy: 0.9600\n",
      "Epoch 192/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1256 - accuracy: 0.9686 - val_loss: 0.1480 - val_accuracy: 0.9600\n",
      "Epoch 193/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1247 - accuracy: 0.9686 - val_loss: 0.1472 - val_accuracy: 0.9600\n",
      "Epoch 194/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1245 - accuracy: 0.9686 - val_loss: 0.1464 - val_accuracy: 0.9600\n",
      "Epoch 195/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1236 - accuracy: 0.9657 - val_loss: 0.1458 - val_accuracy: 0.9600\n",
      "Epoch 196/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1231 - accuracy: 0.9686 - val_loss: 0.1456 - val_accuracy: 0.9600\n",
      "Epoch 197/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1227 - accuracy: 0.9686 - val_loss: 0.1446 - val_accuracy: 0.9667\n",
      "Epoch 198/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1221 - accuracy: 0.9686 - val_loss: 0.1440 - val_accuracy: 0.9667\n",
      "Epoch 199/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1215 - accuracy: 0.9686 - val_loss: 0.1433 - val_accuracy: 0.9667\n",
      "Epoch 200/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1210 - accuracy: 0.9657 - val_loss: 0.1426 - val_accuracy: 0.9667\n",
      "Epoch 201/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1206 - accuracy: 0.9714 - val_loss: 0.1425 - val_accuracy: 0.9600\n",
      "Epoch 202/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1201 - accuracy: 0.9686 - val_loss: 0.1414 - val_accuracy: 0.9667\n",
      "Epoch 203/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1195 - accuracy: 0.9714 - val_loss: 0.1411 - val_accuracy: 0.9667\n",
      "Epoch 204/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1195 - accuracy: 0.9657 - val_loss: 0.1405 - val_accuracy: 0.9667\n",
      "Epoch 205/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1189 - accuracy: 0.9686 - val_loss: 0.1399 - val_accuracy: 0.9667\n",
      "Epoch 206/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1183 - accuracy: 0.9686 - val_loss: 0.1396 - val_accuracy: 0.9667\n",
      "Epoch 207/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1180 - accuracy: 0.9686 - val_loss: 0.1389 - val_accuracy: 0.9667\n",
      "Epoch 208/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1173 - accuracy: 0.9686 - val_loss: 0.1380 - val_accuracy: 0.9667\n",
      "Epoch 209/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1174 - accuracy: 0.9714 - val_loss: 0.1375 - val_accuracy: 0.9667\n",
      "Epoch 210/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1164 - accuracy: 0.9686 - val_loss: 0.1373 - val_accuracy: 0.9667\n",
      "Epoch 211/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1160 - accuracy: 0.9686 - val_loss: 0.1367 - val_accuracy: 0.9667\n",
      "Epoch 212/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1155 - accuracy: 0.9686 - val_loss: 0.1359 - val_accuracy: 0.9667\n",
      "Epoch 213/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1153 - accuracy: 0.9657 - val_loss: 0.1353 - val_accuracy: 0.9667\n",
      "Epoch 214/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1149 - accuracy: 0.9686 - val_loss: 0.1349 - val_accuracy: 0.9667\n",
      "Epoch 215/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1145 - accuracy: 0.9686 - val_loss: 0.1345 - val_accuracy: 0.9667\n",
      "Epoch 216/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1140 - accuracy: 0.9686 - val_loss: 0.1339 - val_accuracy: 0.9667\n",
      "Epoch 217/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1137 - accuracy: 0.9686 - val_loss: 0.1336 - val_accuracy: 0.9667\n",
      "Epoch 218/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1135 - accuracy: 0.9686 - val_loss: 0.1334 - val_accuracy: 0.9667\n",
      "Epoch 219/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1128 - accuracy: 0.9714 - val_loss: 0.1332 - val_accuracy: 0.9667\n",
      "Epoch 220/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1125 - accuracy: 0.9714 - val_loss: 0.1326 - val_accuracy: 0.9667\n",
      "Epoch 221/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1119 - accuracy: 0.9714 - val_loss: 0.1323 - val_accuracy: 0.9667\n",
      "Epoch 222/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1118 - accuracy: 0.9714 - val_loss: 0.1314 - val_accuracy: 0.9667\n",
      "Epoch 223/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1113 - accuracy: 0.9714 - val_loss: 0.1311 - val_accuracy: 0.9667\n",
      "Epoch 224/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1110 - accuracy: 0.9714 - val_loss: 0.1309 - val_accuracy: 0.9667\n",
      "Epoch 225/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1107 - accuracy: 0.9714 - val_loss: 0.1307 - val_accuracy: 0.9667\n",
      "Epoch 226/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1104 - accuracy: 0.9714 - val_loss: 0.1300 - val_accuracy: 0.9667\n",
      "Epoch 227/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1099 - accuracy: 0.9714 - val_loss: 0.1295 - val_accuracy: 0.9667\n",
      "Epoch 228/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1094 - accuracy: 0.9743 - val_loss: 0.1294 - val_accuracy: 0.9667\n",
      "Epoch 229/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1092 - accuracy: 0.9714 - val_loss: 0.1287 - val_accuracy: 0.9667\n",
      "Epoch 230/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1087 - accuracy: 0.9686 - val_loss: 0.1283 - val_accuracy: 0.9667\n",
      "Epoch 231/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1084 - accuracy: 0.9714 - val_loss: 0.1281 - val_accuracy: 0.9667\n",
      "Epoch 232/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1079 - accuracy: 0.9743 - val_loss: 0.1276 - val_accuracy: 0.9667\n",
      "Epoch 233/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1074 - accuracy: 0.9743 - val_loss: 0.1274 - val_accuracy: 0.9667\n",
      "Epoch 234/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1071 - accuracy: 0.9686 - val_loss: 0.1270 - val_accuracy: 0.9667\n",
      "Epoch 235/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1068 - accuracy: 0.9743 - val_loss: 0.1267 - val_accuracy: 0.9667\n",
      "Epoch 236/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1065 - accuracy: 0.9714 - val_loss: 0.1264 - val_accuracy: 0.9667\n",
      "Epoch 237/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1061 - accuracy: 0.9714 - val_loss: 0.1259 - val_accuracy: 0.9667\n",
      "Epoch 238/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1057 - accuracy: 0.9714 - val_loss: 0.1255 - val_accuracy: 0.9667\n",
      "Epoch 239/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1054 - accuracy: 0.9743 - val_loss: 0.1251 - val_accuracy: 0.9667\n",
      "Epoch 240/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1049 - accuracy: 0.9714 - val_loss: 0.1246 - val_accuracy: 0.9667\n",
      "Epoch 241/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1047 - accuracy: 0.9743 - val_loss: 0.1240 - val_accuracy: 0.9733\n",
      "Epoch 242/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1041 - accuracy: 0.9743 - val_loss: 0.1237 - val_accuracy: 0.9667\n",
      "Epoch 243/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1041 - accuracy: 0.9743 - val_loss: 0.1235 - val_accuracy: 0.9667\n",
      "Epoch 244/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1037 - accuracy: 0.9743 - val_loss: 0.1232 - val_accuracy: 0.9667\n",
      "Epoch 245/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1034 - accuracy: 0.9743 - val_loss: 0.1227 - val_accuracy: 0.9733\n",
      "Epoch 246/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1031 - accuracy: 0.9743 - val_loss: 0.1223 - val_accuracy: 0.9667\n",
      "Epoch 247/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1031 - accuracy: 0.9743 - val_loss: 0.1220 - val_accuracy: 0.9667\n",
      "Epoch 248/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1022 - accuracy: 0.9743 - val_loss: 0.1217 - val_accuracy: 0.9667\n",
      "Epoch 249/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1022 - accuracy: 0.9714 - val_loss: 0.1215 - val_accuracy: 0.9667\n",
      "Epoch 250/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1018 - accuracy: 0.9743 - val_loss: 0.1212 - val_accuracy: 0.9667\n",
      "Epoch 251/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1018 - accuracy: 0.9743 - val_loss: 0.1208 - val_accuracy: 0.9667\n",
      "Epoch 252/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1010 - accuracy: 0.9743 - val_loss: 0.1205 - val_accuracy: 0.9667\n",
      "Epoch 253/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1011 - accuracy: 0.9743 - val_loss: 0.1202 - val_accuracy: 0.9667\n",
      "Epoch 254/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1007 - accuracy: 0.9743 - val_loss: 0.1202 - val_accuracy: 0.9667\n",
      "Epoch 255/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1007 - accuracy: 0.9743 - val_loss: 0.1198 - val_accuracy: 0.9667\n",
      "Epoch 256/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1001 - accuracy: 0.9743 - val_loss: 0.1196 - val_accuracy: 0.9667\n",
      "Epoch 257/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.1002 - accuracy: 0.9743 - val_loss: 0.1194 - val_accuracy: 0.9667\n",
      "Epoch 258/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0999 - accuracy: 0.9714 - val_loss: 0.1189 - val_accuracy: 0.9600\n",
      "Epoch 259/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0999 - accuracy: 0.9743 - val_loss: 0.1189 - val_accuracy: 0.9600\n",
      "Epoch 260/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0991 - accuracy: 0.9743 - val_loss: 0.1187 - val_accuracy: 0.9667\n",
      "Epoch 261/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0990 - accuracy: 0.9743 - val_loss: 0.1184 - val_accuracy: 0.9667\n",
      "Epoch 262/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0988 - accuracy: 0.9743 - val_loss: 0.1180 - val_accuracy: 0.9667\n",
      "Epoch 263/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0987 - accuracy: 0.9743 - val_loss: 0.1177 - val_accuracy: 0.9667\n",
      "Epoch 264/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0983 - accuracy: 0.9743 - val_loss: 0.1177 - val_accuracy: 0.9600\n",
      "Epoch 265/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0977 - accuracy: 0.9743 - val_loss: 0.1175 - val_accuracy: 0.9667\n",
      "Epoch 266/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0977 - accuracy: 0.9714 - val_loss: 0.1171 - val_accuracy: 0.9667\n",
      "Epoch 267/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0979 - accuracy: 0.9743 - val_loss: 0.1167 - val_accuracy: 0.9600\n",
      "Epoch 268/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0975 - accuracy: 0.9743 - val_loss: 0.1165 - val_accuracy: 0.9667\n",
      "Epoch 269/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0974 - accuracy: 0.9743 - val_loss: 0.1164 - val_accuracy: 0.9733\n",
      "Epoch 270/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0968 - accuracy: 0.9743 - val_loss: 0.1161 - val_accuracy: 0.9667\n",
      "Epoch 271/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0968 - accuracy: 0.9743 - val_loss: 0.1160 - val_accuracy: 0.9667\n",
      "Epoch 272/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0970 - accuracy: 0.9743 - val_loss: 0.1154 - val_accuracy: 0.9667\n",
      "Epoch 273/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0966 - accuracy: 0.9743 - val_loss: 0.1153 - val_accuracy: 0.9667\n",
      "Epoch 274/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0963 - accuracy: 0.9743 - val_loss: 0.1151 - val_accuracy: 0.9667\n",
      "Epoch 275/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0959 - accuracy: 0.9743 - val_loss: 0.1150 - val_accuracy: 0.9667\n",
      "Epoch 276/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0955 - accuracy: 0.9743 - val_loss: 0.1145 - val_accuracy: 0.9667\n",
      "Epoch 277/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0957 - accuracy: 0.9743 - val_loss: 0.1143 - val_accuracy: 0.9667\n",
      "Epoch 278/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0955 - accuracy: 0.9743 - val_loss: 0.1143 - val_accuracy: 0.9667\n",
      "Epoch 279/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0952 - accuracy: 0.9743 - val_loss: 0.1140 - val_accuracy: 0.9667\n",
      "Epoch 280/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0949 - accuracy: 0.9743 - val_loss: 0.1136 - val_accuracy: 0.9667\n",
      "Epoch 281/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0947 - accuracy: 0.9743 - val_loss: 0.1132 - val_accuracy: 0.9667\n",
      "Epoch 282/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0951 - accuracy: 0.9743 - val_loss: 0.1130 - val_accuracy: 0.9667\n",
      "Epoch 283/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0943 - accuracy: 0.9743 - val_loss: 0.1130 - val_accuracy: 0.9667\n",
      "Epoch 284/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0942 - accuracy: 0.9743 - val_loss: 0.1131 - val_accuracy: 0.9667\n",
      "Epoch 285/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0942 - accuracy: 0.9714 - val_loss: 0.1127 - val_accuracy: 0.9667\n",
      "Epoch 286/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0940 - accuracy: 0.9743 - val_loss: 0.1124 - val_accuracy: 0.9667\n",
      "Epoch 287/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0938 - accuracy: 0.9714 - val_loss: 0.1121 - val_accuracy: 0.9667\n",
      "Epoch 288/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0935 - accuracy: 0.9743 - val_loss: 0.1119 - val_accuracy: 0.9667\n",
      "Epoch 289/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0931 - accuracy: 0.9743 - val_loss: 0.1117 - val_accuracy: 0.9667\n",
      "Epoch 290/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0931 - accuracy: 0.9714 - val_loss: 0.1117 - val_accuracy: 0.9667\n",
      "Epoch 291/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0931 - accuracy: 0.9743 - val_loss: 0.1113 - val_accuracy: 0.9667\n",
      "Epoch 292/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0928 - accuracy: 0.9743 - val_loss: 0.1113 - val_accuracy: 0.9667\n",
      "Epoch 293/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0925 - accuracy: 0.9743 - val_loss: 0.1110 - val_accuracy: 0.9667\n",
      "Epoch 294/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0925 - accuracy: 0.9743 - val_loss: 0.1106 - val_accuracy: 0.9667\n",
      "Epoch 295/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0923 - accuracy: 0.9743 - val_loss: 0.1105 - val_accuracy: 0.9667\n",
      "Epoch 296/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0923 - accuracy: 0.9686 - val_loss: 0.1103 - val_accuracy: 0.9667\n",
      "Epoch 297/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0920 - accuracy: 0.9743 - val_loss: 0.1101 - val_accuracy: 0.9667\n",
      "Epoch 298/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0918 - accuracy: 0.9714 - val_loss: 0.1099 - val_accuracy: 0.9667\n",
      "Epoch 299/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0917 - accuracy: 0.9743 - val_loss: 0.1097 - val_accuracy: 0.9667\n",
      "Epoch 300/300\n",
      "11/11 [==============================] - 0s 3ms/step - loss: 0.0913 - accuracy: 0.9714 - val_loss: 0.1098 - val_accuracy: 0.9667\n"
     ]
    }
   ],