From 3be7e6a5405171a0d86aa115e7899a0d886c2ee8 Mon Sep 17 00:00:00 2001
From: Tarun Chadha <tarunchadha23@gmail.com>
Date: Wed, 24 Apr 2019 21:52:43 +0200
Subject: [PATCH] Keras SciKit wrapper-v1

---
 neural_nets_intro.ipynb | 1491 +++++++++++++++++++++++++++++++++++----
 1 file changed, 1336 insertions(+), 155 deletions(-)

diff --git a/neural_nets_intro.ipynb b/neural_nets_intro.ipynb
index 6586ddf..f61f012 100644
--- a/neural_nets_intro.ipynb
+++ b/neural_nets_intro.ipynb
@@ -572,7 +572,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**TO DO: Move this example after the previous dataset examples**"
+    "**TO DO: Move the MNIST example after the previous dataset examples**"
    ]
   },
   {
@@ -928,21 +928,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x7fe91c822048>"
+       "<Figure size 360x360 with 1 Axes>"
       ]
      },
      "metadata": {
-      "image/png": {
-       "height": 318,
-       "width": 332
-      },
       "needs_background": "light"
      },
      "output_type": "display_data"
@@ -967,151 +977,1370 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 126,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sklearn.model_selection import train_test_split\n",
-    "from keras.models import Sequential\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 = xor.iloc[:, -1].astype(int)\n",
     "\n",
-    "# Here we split the dataset into training (80%) and validation sets (20%) \n",
-    "X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.2)\n",
-    "\n",
-    "\n",
     "# Building a Keras model\n",
     "\n",
-    "model = Sequential()\n",
+    "def a_simple_NN():\n",
+    "    \n",
+    "    model = Sequential()\n",
     "\n",
-    "model.add(Dense(4, input_shape = (2,), activation = \"relu\"))\n",
+    "    model.add(Dense(4, input_shape = (2,), activation = \"relu\"))\n",
     "\n",
-    "model.add(Dense(4, activation = \"relu\"))\n",
+    "    model.add(Dense(4, activation = \"relu\"))\n",
     "\n",
-    "model.add(Dense(1, activation = \"sigmoid\"))\n",
+    "    model.add(Dense(1, activation = \"sigmoid\"))\n",
     "\n",
-    "model.compile(loss=\"binary_crossentropy\", optimizer=\"rmsprop\", metrics=[\"accuracy\"])\n",
-    "\n",
-    "num_epochs = 200\n",
+    "    model.compile(loss=\"binary_crossentropy\", optimizer=\"rmsprop\", metrics=[\"accuracy\"])\n",
+    "    \n",
+    "    return model\n",
     "\n",
-    "model_run = model.fit(X_train, y_train, epochs=num_epochs, validation_data = (X_test,y_test))\n"
+    "model = a_simple_NN()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 125,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x7fe9005c57b8>]"
-      ]
-     },
-     "execution_count": 125,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train on 350 samples, validate on 150 samples\n",
+      "Epoch 1/100\n",
+      "350/350 [==============================] - 0s 83us/step - loss: 0.3633 - acc: 0.7457 - val_loss: 0.3889 - val_acc: 0.7733\n",
+      "Epoch 2/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3632 - acc: 0.7457 - val_loss: 0.3894 - val_acc: 0.7733\n",
+      "Epoch 3/100\n",
+      "350/350 [==============================] - 0s 150us/step - loss: 0.3629 - acc: 0.7429 - val_loss: 0.3898 - val_acc: 0.7667\n",
+      "Epoch 4/100\n",
+      "350/350 [==============================] - 0s 75us/step - loss: 0.3627 - acc: 0.7429 - val_loss: 0.3903 - val_acc: 0.7667\n",
+      "Epoch 5/100\n",
+      "350/350 [==============================] - 0s 80us/step - loss: 0.3626 - acc: 0.7457 - val_loss: 0.3904 - val_acc: 0.7667\n",
+      "Epoch 6/100\n",
+      "350/350 [==============================] - 0s 108us/step - loss: 0.3627 - acc: 0.7457 - val_loss: 0.3905 - val_acc: 0.7667\n",
+      "Epoch 7/100\n",
+      "350/350 [==============================] - 0s 103us/step - loss: 0.3627 - acc: 0.7457 - val_loss: 0.3906 - val_acc: 0.7667\n",
+      "Epoch 8/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3625 - acc: 0.7457 - val_loss: 0.3909 - val_acc: 0.7667\n",
+      "Epoch 9/100\n",
+      "350/350 [==============================] - 0s 88us/step - loss: 0.3625 - acc: 0.7457 - val_loss: 0.3912 - val_acc: 0.7667\n",
+      "Epoch 10/100\n",
+      "350/350 [==============================] - 0s 97us/step - loss: 0.3627 - acc: 0.7457 - val_loss: 0.3912 - val_acc: 0.7667\n",
+      "Epoch 11/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3627 - acc: 0.7457 - val_loss: 0.3912 - val_acc: 0.7667\n",
+      "Epoch 12/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3914 - val_acc: 0.7667\n",
+      "Epoch 13/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3626 - acc: 0.7457 - val_loss: 0.3916 - val_acc: 0.7667\n",
+      "Epoch 14/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3626 - acc: 0.7457 - val_loss: 0.3917 - val_acc: 0.7667\n",
+      "Epoch 15/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3627 - acc: 0.7457 - val_loss: 0.3916 - val_acc: 0.7667\n",
+      "Epoch 16/100\n",
+      "350/350 [==============================] - 0s 106us/step - loss: 0.3625 - acc: 0.7486 - val_loss: 0.3915 - val_acc: 0.7667\n",
+      "Epoch 17/100\n",
+      "350/350 [==============================] - 0s 102us/step - loss: 0.3625 - acc: 0.7457 - val_loss: 0.3917 - val_acc: 0.7667\n",
+      "Epoch 18/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3919 - val_acc: 0.7667\n",
+      "Epoch 19/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3624 - acc: 0.7457 - val_loss: 0.3918 - val_acc: 0.7667\n",
+      "Epoch 20/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3626 - acc: 0.7486 - val_loss: 0.3920 - val_acc: 0.7667\n",
+      "Epoch 21/100\n",
+      "350/350 [==============================] - 0s 105us/step - loss: 0.3624 - acc: 0.7486 - val_loss: 0.3920 - val_acc: 0.7667\n",
+      "Epoch 22/100\n",
+      "350/350 [==============================] - 0s 95us/step - loss: 0.3622 - acc: 0.7457 - val_loss: 0.3919 - val_acc: 0.7667\n",
+      "Epoch 23/100\n",
+      "350/350 [==============================] - 0s 102us/step - loss: 0.3624 - acc: 0.7486 - val_loss: 0.3920 - val_acc: 0.7667\n",
+      "Epoch 24/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3920 - val_acc: 0.7667\n",
+      "Epoch 25/100\n",
+      "350/350 [==============================] - 0s 105us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3922 - val_acc: 0.7667\n",
+      "Epoch 26/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3923 - val_acc: 0.7667\n",
+      "Epoch 27/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3624 - acc: 0.7486 - val_loss: 0.3923 - val_acc: 0.7667\n",
+      "Epoch 28/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3622 - acc: 0.7486 - val_loss: 0.3921 - val_acc: 0.7667\n",
+      "Epoch 29/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3621 - acc: 0.7486 - val_loss: 0.3921 - val_acc: 0.7667\n",
+      "Epoch 30/100\n",
+      "350/350 [==============================] - 0s 90us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3923 - val_acc: 0.7667\n",
+      "Epoch 31/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3622 - acc: 0.7486 - val_loss: 0.3924 - val_acc: 0.7667\n",
+      "Epoch 32/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3622 - acc: 0.7486 - val_loss: 0.3925 - val_acc: 0.7667\n",
+      "Epoch 33/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3623 - acc: 0.7486 - val_loss: 0.3926 - val_acc: 0.7667\n",
+      "Epoch 34/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3620 - acc: 0.7486 - val_loss: 0.3927 - val_acc: 0.7667\n",
+      "Epoch 35/100\n",
+      "350/350 [==============================] - 0s 85us/step - loss: 0.3621 - acc: 0.7486 - val_loss: 0.3927 - val_acc: 0.7667\n",
+      "Epoch 36/100\n",
+      "350/350 [==============================] - 0s 112us/step - loss: 0.3622 - acc: 0.7486 - val_loss: 0.3926 - val_acc: 0.7667\n",
+      "Epoch 37/100\n",
+      "350/350 [==============================] - 0s 87us/step - loss: 0.3621 - acc: 0.7486 - val_loss: 0.3926 - val_acc: 0.7667\n",
+      "Epoch 38/100\n",
+      "350/350 [==============================] - 0s 122us/step - loss: 0.3620 - acc: 0.7486 - val_loss: 0.3927 - val_acc: 0.7667\n",
+      "Epoch 39/100\n",
+      "350/350 [==============================] - 0s 87us/step - loss: 0.3620 - acc: 0.7457 - val_loss: 0.3926 - val_acc: 0.7667\n",
+      "Epoch 40/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3620 - acc: 0.7486 - val_loss: 0.3928 - val_acc: 0.7667\n",
+      "Epoch 41/100\n",
+      "350/350 [==============================] - 0s 80us/step - loss: 0.3618 - acc: 0.7457 - val_loss: 0.3929 - val_acc: 0.7667\n",
+      "Epoch 42/100\n",
+      "350/350 [==============================] - 0s 82us/step - loss: 0.3622 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 43/100\n",
+      "350/350 [==============================] - 0s 100us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 44/100\n",
+      "350/350 [==============================] - 0s 111us/step - loss: 0.3619 - acc: 0.7486 - val_loss: 0.3931 - val_acc: 0.7667\n",
+      "Epoch 45/100\n",
+      "350/350 [==============================] - 0s 80us/step - loss: 0.3621 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 46/100\n",
+      "350/350 [==============================] - 0s 104us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3931 - val_acc: 0.7667\n",
+      "Epoch 47/100\n",
+      "350/350 [==============================] - 0s 88us/step - loss: 0.3619 - acc: 0.7486 - val_loss: 0.3931 - val_acc: 0.7667\n",
+      "Epoch 48/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3621 - acc: 0.7486 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 49/100\n",
+      "350/350 [==============================] - 0s 98us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 50/100\n",
+      "350/350 [==============================] - 0s 104us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 51/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3618 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 52/100\n",
+      "350/350 [==============================] - 0s 103us/step - loss: 0.3620 - acc: 0.7486 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 53/100\n",
+      "350/350 [==============================] - 0s 101us/step - loss: 0.3618 - acc: 0.7486 - val_loss: 0.3931 - val_acc: 0.7667\n",
+      "Epoch 54/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3931 - val_acc: 0.7667\n",
+      "Epoch 55/100\n",
+      "350/350 [==============================] - 0s 102us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 56/100\n",
+      "350/350 [==============================] - 0s 86us/step - loss: 0.3618 - acc: 0.7486 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 57/100\n",
+      "350/350 [==============================] - 0s 86us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3929 - val_acc: 0.7667\n",
+      "Epoch 58/100\n",
+      "350/350 [==============================] - 0s 97us/step - loss: 0.3620 - acc: 0.7457 - val_loss: 0.3930 - val_acc: 0.7667\n",
+      "Epoch 59/100\n",
+      "350/350 [==============================] - 0s 78us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3932 - val_acc: 0.7667\n",
+      "Epoch 60/100\n",
+      "350/350 [==============================] - 0s 95us/step - loss: 0.3618 - acc: 0.7486 - val_loss: 0.3932 - val_acc: 0.7667\n",
+      "Epoch 61/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "350/350 [==============================] - 0s 88us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3932 - val_acc: 0.7667\n",
+      "Epoch 62/100\n",
+      "350/350 [==============================] - 0s 97us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3933 - val_acc: 0.7667\n",
+      "Epoch 63/100\n",
+      "350/350 [==============================] - 0s 106us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3935 - val_acc: 0.7667\n",
+      "Epoch 64/100\n",
+      "350/350 [==============================] - 0s 95us/step - loss: 0.3619 - acc: 0.7457 - val_loss: 0.3936 - val_acc: 0.7667\n",
+      "Epoch 65/100\n",
+      "350/350 [==============================] - 0s 101us/step - loss: 0.3618 - acc: 0.7457 - val_loss: 0.3936 - val_acc: 0.7667\n",
+      "Epoch 66/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3617 - acc: 0.7486 - val_loss: 0.3937 - val_acc: 0.7667\n",
+      "Epoch 67/100\n",
+      "350/350 [==============================] - 0s 98us/step - loss: 0.3616 - acc: 0.7486 - val_loss: 0.3937 - val_acc: 0.7667\n",
+      "Epoch 68/100\n",
+      "350/350 [==============================] - 0s 93us/step - loss: 0.3618 - acc: 0.7457 - val_loss: 0.3939 - val_acc: 0.7667\n",
+      "Epoch 69/100\n",
+      "350/350 [==============================] - 0s 84us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3938 - val_acc: 0.7667\n",
+      "Epoch 70/100\n",
+      "350/350 [==============================] - 0s 90us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3939 - val_acc: 0.7667\n",
+      "Epoch 71/100\n",
+      "350/350 [==============================] - 0s 98us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3939 - val_acc: 0.7667\n",
+      "Epoch 72/100\n",
+      "350/350 [==============================] - 0s 90us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3938 - val_acc: 0.7667\n",
+      "Epoch 73/100\n",
+      "350/350 [==============================] - 0s 89us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3941 - val_acc: 0.7667\n",
+      "Epoch 74/100\n",
+      "350/350 [==============================] - 0s 95us/step - loss: 0.3615 - acc: 0.7486 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 75/100\n",
+      "350/350 [==============================] - 0s 90us/step - loss: 0.3614 - acc: 0.7457 - val_loss: 0.3942 - val_acc: 0.7667\n",
+      "Epoch 76/100\n",
+      "350/350 [==============================] - 0s 81us/step - loss: 0.3617 - acc: 0.7486 - val_loss: 0.3940 - val_acc: 0.7667\n",
+      "Epoch 77/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3941 - val_acc: 0.7667\n",
+      "Epoch 78/100\n",
+      "350/350 [==============================] - 0s 103us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 79/100\n",
+      "350/350 [==============================] - 0s 65us/step - loss: 0.3616 - acc: 0.7486 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 80/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 81/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 82/100\n",
+      "350/350 [==============================] - 0s 95us/step - loss: 0.3617 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 83/100\n",
+      "350/350 [==============================] - 0s 107us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3946 - val_acc: 0.7667\n",
+      "Epoch 84/100\n",
+      "350/350 [==============================] - 0s 93us/step - loss: 0.3614 - acc: 0.7486 - val_loss: 0.3947 - val_acc: 0.7667\n",
+      "Epoch 85/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3614 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 86/100\n",
+      "350/350 [==============================] - 0s 102us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 87/100\n",
+      "350/350 [==============================] - 0s 91us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 88/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3614 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 89/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 90/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 91/100\n",
+      "350/350 [==============================] - 0s 93us/step - loss: 0.3615 - acc: 0.7429 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 92/100\n",
+      "350/350 [==============================] - 0s 90us/step - loss: 0.3618 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 93/100\n",
+      "350/350 [==============================] - 0s 74us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 94/100\n",
+      "350/350 [==============================] - 0s 94us/step - loss: 0.3614 - acc: 0.7486 - val_loss: 0.3942 - val_acc: 0.7667\n",
+      "Epoch 95/100\n",
+      "350/350 [==============================] - 0s 96us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 96/100\n",
+      "350/350 [==============================] - 0s 99us/step - loss: 0.3613 - acc: 0.7457 - val_loss: 0.3943 - val_acc: 0.7667\n",
+      "Epoch 97/100\n",
+      "350/350 [==============================] - 0s 98us/step - loss: 0.3616 - acc: 0.7457 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 98/100\n",
+      "350/350 [==============================] - 0s 93us/step - loss: 0.3615 - acc: 0.7457 - val_loss: 0.3945 - val_acc: 0.7667\n",
+      "Epoch 99/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3612 - acc: 0.7486 - val_loss: 0.3944 - val_acc: 0.7667\n",
+      "Epoch 100/100\n",
+      "350/350 [==============================] - 0s 92us/step - loss: 0.3614 - acc: 0.7457 - val_loss: 0.3944 - val_acc: 0.7667\n"
+     ]
     },
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x7fe9005c5cc0>"
+       "<Figure size 432x288 with 1 Axes>"
       ]
      },
      "metadata": {
-      "image/png": {
-       "height": 250,
-       "width": 380
-      },
       "needs_background": "light"
      },
      "output_type": "display_data"
     }
    ],
    "source": [
-    "import matplotlib.pyplot as plt\n",
+    "# Here we split the dataset into training (80%) and validation sets (20%) \n",
+    "X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.3)\n",
+    "\n",
+    "num_epochs = 100\n",
+    "\n",
+    "model_run = model.fit(X_train, y_train, epochs=num_epochs, validation_data = (X_test,y_test))\n",
     "\n",
     "history_model = model_run.history\n",
     "\n",
-    "plt.plot(np.arange(1,num_epochs+1)[5:], history_model[\"acc\"][5:], \"--\")\n",
+    "plt.plot(np.arange(1,num_epochs+1)[5:], history_model[\"acc\"][5:], \"--\") ;\n",
     "\n",
-    "plt.plot(np.arange(1,num_epochs+1)[5:], history_model[\"val_acc\"][5:])"
+    "plt.plot(np.arange(1,num_epochs+1)[5:], history_model[\"val_acc\"][5:]) ;"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using SciKit learn functions on Keras models\n",
+    "\n",
+    "As we have seen from the previous chapters, SciKit learn offers very handy functions for evaluating and tuning the machine learning models.\n",
+    "\n",
+    "So the question is: Can we somehow use those functions with the models we build in Keras?\n",
+    "\n",
+    "The Answer is **YES !**\n",
+    "\n",
+    "Keras offers wrappers which allow its Sequential models to be used with SciKit learn. There 2 such wrappers: **KerasClassifier** and **KerasRegressor**.\n",
+    "\n",
+    "For more information:\n",
+    "https://keras.io/scikit-learn-api/\n",
+    "\n",
+    "**Now lets see how this works!**"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 132,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "280/280 [==============================] - 1s 3ms/step - loss: 0.9489 - acc: 0.3321\n",
+      "Epoch 2/100\n",
+      "280/280 [==============================] - 0s 98us/step - loss: 0.9255 - acc: 0.3321\n",
+      "Epoch 3/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.9084 - acc: 0.3429\n",
+      "Epoch 4/100\n",
+      "280/280 [==============================] - 0s 141us/step - loss: 0.8940 - acc: 0.3357\n",
+      "Epoch 5/100\n",
+      "280/280 [==============================] - 0s 117us/step - loss: 0.8808 - acc: 0.3464\n",
+      "Epoch 6/100\n",
+      "280/280 [==============================] - 0s 126us/step - loss: 0.8685 - acc: 0.3393\n",
+      "Epoch 7/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.8571 - acc: 0.3357\n",
+      "Epoch 8/100\n",
+      "280/280 [==============================] - 0s 73us/step - loss: 0.8462 - acc: 0.3393\n",
+      "Epoch 9/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.8360 - acc: 0.3321\n",
+      "Epoch 10/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.8264 - acc: 0.3286\n",
+      "Epoch 11/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.8170 - acc: 0.3321\n",
+      "Epoch 12/100\n",
+      "280/280 [==============================] - 0s 95us/step - loss: 0.8079 - acc: 0.3321\n",
+      "Epoch 13/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.7991 - acc: 0.3321\n",
+      "Epoch 14/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.7907 - acc: 0.3286\n",
+      "Epoch 15/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.7828 - acc: 0.3393\n",
+      "Epoch 16/100\n",
+      "280/280 [==============================] - 0s 115us/step - loss: 0.7749 - acc: 0.3500\n",
+      "Epoch 17/100\n",
+      "280/280 [==============================] - 0s 84us/step - loss: 0.7673 - acc: 0.3536\n",
+      "Epoch 18/100\n",
+      "280/280 [==============================] - 0s 96us/step - loss: 0.7602 - acc: 0.3536\n",
+      "Epoch 19/100\n",
+      "280/280 [==============================] - 0s 112us/step - loss: 0.7535 - acc: 0.3571\n",
+      "Epoch 20/100\n",
+      "280/280 [==============================] - 0s 110us/step - loss: 0.7468 - acc: 0.3643\n",
+      "Epoch 21/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.7405 - acc: 0.3750\n",
+      "Epoch 22/100\n",
+      "280/280 [==============================] - 0s 99us/step - loss: 0.7345 - acc: 0.3821\n",
+      "Epoch 23/100\n",
+      "280/280 [==============================] - 0s 98us/step - loss: 0.7290 - acc: 0.3893\n",
+      "Epoch 24/100\n",
+      "280/280 [==============================] - 0s 107us/step - loss: 0.7235 - acc: 0.3857\n",
+      "Epoch 25/100\n",
+      "280/280 [==============================] - 0s 84us/step - loss: 0.7184 - acc: 0.3893\n",
+      "Epoch 26/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.7134 - acc: 0.3893\n",
+      "Epoch 27/100\n",
+      "280/280 [==============================] - 0s 96us/step - loss: 0.7084 - acc: 0.4036\n",
+      "Epoch 28/100\n",
+      "280/280 [==============================] - 0s 108us/step - loss: 0.7037 - acc: 0.4071\n",
+      "Epoch 29/100\n",
+      "280/280 [==============================] - 0s 99us/step - loss: 0.6993 - acc: 0.4107\n",
+      "Epoch 30/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.6951 - acc: 0.4250\n",
+      "Epoch 31/100\n",
+      "280/280 [==============================] - 0s 105us/step - loss: 0.6908 - acc: 0.4321\n",
+      "Epoch 32/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6867 - acc: 0.4464\n",
+      "Epoch 33/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.6826 - acc: 0.4607\n",
+      "Epoch 34/100\n",
+      "280/280 [==============================] - 0s 109us/step - loss: 0.6785 - acc: 0.4714\n",
+      "Epoch 35/100\n",
+      "280/280 [==============================] - 0s 98us/step - loss: 0.6746 - acc: 0.5071\n",
+      "Epoch 36/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.6708 - acc: 0.5179\n",
+      "Epoch 37/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6670 - acc: 0.5250\n",
+      "Epoch 38/100\n",
+      "280/280 [==============================] - 0s 106us/step - loss: 0.6634 - acc: 0.5286\n",
+      "Epoch 39/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6599 - acc: 0.5429\n",
+      "Epoch 40/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6563 - acc: 0.5643\n",
+      "Epoch 41/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6529 - acc: 0.5857\n",
+      "Epoch 42/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6495 - acc: 0.6071\n",
+      "Epoch 43/100\n",
+      "280/280 [==============================] - 0s 99us/step - loss: 0.6461 - acc: 0.6107\n",
+      "Epoch 44/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6426 - acc: 0.6143\n",
+      "Epoch 45/100\n",
+      "280/280 [==============================] - 0s 92us/step - loss: 0.6390 - acc: 0.6500\n",
+      "Epoch 46/100\n",
+      "280/280 [==============================] - 0s 101us/step - loss: 0.6355 - acc: 0.6679\n",
+      "Epoch 47/100\n",
+      "280/280 [==============================] - 0s 103us/step - loss: 0.6321 - acc: 0.6821\n",
+      "Epoch 48/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.6287 - acc: 0.6893\n",
+      "Epoch 49/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6254 - acc: 0.6964\n",
+      "Epoch 50/100\n",
+      "280/280 [==============================] - 0s 98us/step - loss: 0.6220 - acc: 0.7036\n",
+      "Epoch 51/100\n",
+      "280/280 [==============================] - 0s 92us/step - loss: 0.6185 - acc: 0.7107\n",
+      "Epoch 52/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6152 - acc: 0.7250\n",
+      "Epoch 53/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.6120 - acc: 0.7250\n",
+      "Epoch 54/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6087 - acc: 0.7393\n",
+      "Epoch 55/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.6057 - acc: 0.7286\n",
+      "Epoch 56/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.6026 - acc: 0.7429\n",
+      "Epoch 57/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5995 - acc: 0.7393\n",
+      "Epoch 58/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.5966 - acc: 0.7429\n",
+      "Epoch 59/100\n",
+      "280/280 [==============================] - 0s 81us/step - loss: 0.5934 - acc: 0.7536\n",
+      "Epoch 60/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.5905 - acc: 0.7571\n",
+      "Epoch 61/100\n",
+      "280/280 [==============================] - 0s 87us/step - loss: 0.5878 - acc: 0.7571\n",
+      "Epoch 62/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.5850 - acc: 0.7571\n",
+      "Epoch 63/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.5823 - acc: 0.7571\n",
+      "Epoch 64/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.5795 - acc: 0.7607\n",
+      "Epoch 65/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.5766 - acc: 0.7536\n",
+      "Epoch 66/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.5738 - acc: 0.7679\n",
+      "Epoch 67/100\n",
+      "280/280 [==============================] - 0s 87us/step - loss: 0.5714 - acc: 0.7679\n",
+      "Epoch 68/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5687 - acc: 0.7643\n",
+      "Epoch 69/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5662 - acc: 0.7679\n",
+      "Epoch 70/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.5635 - acc: 0.7714\n",
+      "Epoch 71/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5610 - acc: 0.7714\n",
+      "Epoch 72/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.5583 - acc: 0.7750\n",
+      "Epoch 73/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.5559 - acc: 0.7750\n",
+      "Epoch 74/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.5533 - acc: 0.7750\n",
+      "Epoch 75/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.5507 - acc: 0.7750\n",
+      "Epoch 76/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5482 - acc: 0.7714\n",
+      "Epoch 77/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5458 - acc: 0.7821\n",
+      "Epoch 78/100\n",
+      "280/280 [==============================] - 0s 87us/step - loss: 0.5434 - acc: 0.7786\n",
+      "Epoch 79/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.5409 - acc: 0.7857\n",
+      "Epoch 80/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.5387 - acc: 0.7893\n",
+      "Epoch 81/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5364 - acc: 0.7893\n",
+      "Epoch 82/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.5341 - acc: 0.7893\n",
+      "Epoch 83/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.5318 - acc: 0.7929\n",
+      "Epoch 84/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 89us/step - loss: 0.5294 - acc: 0.7929\n",
+      "Epoch 85/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.5271 - acc: 0.7929\n",
+      "Epoch 86/100\n",
+      "280/280 [==============================] - 0s 87us/step - loss: 0.5248 - acc: 0.7929\n",
+      "Epoch 87/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.5223 - acc: 0.7929\n",
+      "Epoch 88/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.5201 - acc: 0.7929\n",
+      "Epoch 89/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.5179 - acc: 0.7893\n",
+      "Epoch 90/100\n",
+      "280/280 [==============================] - 0s 75us/step - loss: 0.5158 - acc: 0.7893\n",
+      "Epoch 91/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.5135 - acc: 0.7893\n",
+      "Epoch 92/100\n",
+      "280/280 [==============================] - 0s 84us/step - loss: 0.5114 - acc: 0.7893\n",
+      "Epoch 93/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5091 - acc: 0.7929\n",
+      "Epoch 94/100\n",
+      "280/280 [==============================] - 0s 81us/step - loss: 0.5072 - acc: 0.7964\n",
+      "Epoch 95/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.5050 - acc: 0.8000\n",
+      "Epoch 96/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.5032 - acc: 0.7964\n",
+      "Epoch 97/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5012 - acc: 0.7964\n",
+      "Epoch 98/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.4993 - acc: 0.7964\n",
+      "Epoch 99/100\n",
+      "280/280 [==============================] - 0s 104us/step - loss: 0.4976 - acc: 0.7929\n",
+      "Epoch 100/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.4958 - acc: 0.7929\n",
+      "70/70 [==============================] - 0s 3ms/step\n",
+      "Epoch 1/100\n",
+      "280/280 [==============================] - 1s 4ms/step - loss: 0.9036 - acc: 0.3107\n",
+      "Epoch 2/100\n",
+      "280/280 [==============================] - 0s 129us/step - loss: 0.8788 - acc: 0.2143\n",
+      "Epoch 3/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.8610 - acc: 0.1821\n",
+      "Epoch 4/100\n",
+      "280/280 [==============================] - 0s 126us/step - loss: 0.8447 - acc: 0.1643\n",
+      "Epoch 5/100\n",
+      "280/280 [==============================] - 0s 104us/step - loss: 0.8288 - acc: 0.1750\n",
+      "Epoch 6/100\n",
+      "280/280 [==============================] - 0s 121us/step - loss: 0.8148 - acc: 0.1750\n",
+      "Epoch 7/100\n",
+      "280/280 [==============================] - 0s 123us/step - loss: 0.8015 - acc: 0.1786\n",
+      "Epoch 8/100\n",
+      "280/280 [==============================] - 0s 118us/step - loss: 0.7890 - acc: 0.1714\n",
+      "Epoch 9/100\n",
+      "280/280 [==============================] - 0s 101us/step - loss: 0.7776 - acc: 0.1786\n",
+      "Epoch 10/100\n",
+      "280/280 [==============================] - 0s 108us/step - loss: 0.7665 - acc: 0.1821\n",
+      "Epoch 11/100\n",
+      "280/280 [==============================] - 0s 111us/step - loss: 0.7560 - acc: 0.1964\n",
+      "Epoch 12/100\n",
+      "280/280 [==============================] - 0s 102us/step - loss: 0.7466 - acc: 0.2179\n",
+      "Epoch 13/100\n",
+      "280/280 [==============================] - 0s 110us/step - loss: 0.7379 - acc: 0.2357\n",
+      "Epoch 14/100\n",
+      "280/280 [==============================] - 0s 97us/step - loss: 0.7294 - acc: 0.2786\n",
+      "Epoch 15/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.7220 - acc: 0.3036\n",
+      "Epoch 16/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.7153 - acc: 0.3143\n",
+      "Epoch 17/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.7096 - acc: 0.3607\n",
+      "Epoch 18/100\n",
+      "280/280 [==============================] - 0s 95us/step - loss: 0.7049 - acc: 0.3821\n",
+      "Epoch 19/100\n",
+      "280/280 [==============================] - 0s 112us/step - loss: 0.7008 - acc: 0.4107\n",
+      "Epoch 20/100\n",
+      "280/280 [==============================] - 0s 107us/step - loss: 0.6977 - acc: 0.4571\n",
+      "Epoch 21/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6954 - acc: 0.4607\n",
+      "Epoch 22/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.6936 - acc: 0.4714\n",
+      "Epoch 23/100\n",
+      "280/280 [==============================] - 0s 99us/step - loss: 0.6922 - acc: 0.4750\n",
+      "Epoch 24/100\n",
+      "280/280 [==============================] - 0s 84us/step - loss: 0.6908 - acc: 0.4821\n",
+      "Epoch 25/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6896 - acc: 0.4821\n",
+      "Epoch 26/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6886 - acc: 0.4857\n",
+      "Epoch 27/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.6875 - acc: 0.4893\n",
+      "Epoch 28/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.6864 - acc: 0.4964\n",
+      "Epoch 29/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.6851 - acc: 0.4964\n",
+      "Epoch 30/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.6838 - acc: 0.4964\n",
+      "Epoch 31/100\n",
+      "280/280 [==============================] - 0s 98us/step - loss: 0.6823 - acc: 0.4964\n",
+      "Epoch 32/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6807 - acc: 0.4964\n",
+      "Epoch 33/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6788 - acc: 0.4964\n",
+      "Epoch 34/100\n",
+      "280/280 [==============================] - 0s 87us/step - loss: 0.6770 - acc: 0.4964\n",
+      "Epoch 35/100\n",
+      "280/280 [==============================] - 0s 162us/step - loss: 0.6749 - acc: 0.4964\n",
+      "Epoch 36/100\n",
+      "280/280 [==============================] - 0s 112us/step - loss: 0.6728 - acc: 0.4964\n",
+      "Epoch 37/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.6706 - acc: 0.4964\n",
+      "Epoch 38/100\n",
+      "280/280 [==============================] - 0s 97us/step - loss: 0.6683 - acc: 0.4964\n",
+      "Epoch 39/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6661 - acc: 0.4964\n",
+      "Epoch 40/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6638 - acc: 0.5071\n",
+      "Epoch 41/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.6614 - acc: 0.6821\n",
+      "Epoch 42/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6590 - acc: 0.6893\n",
+      "Epoch 43/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.6566 - acc: 0.6821\n",
+      "Epoch 44/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6542 - acc: 0.6821\n",
+      "Epoch 45/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.6519 - acc: 0.6821\n",
+      "Epoch 46/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6496 - acc: 0.6821\n",
+      "Epoch 47/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6473 - acc: 0.6964\n",
+      "Epoch 48/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6449 - acc: 0.7071\n",
+      "Epoch 49/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6425 - acc: 0.7000\n",
+      "Epoch 50/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.6401 - acc: 0.7000\n",
+      "Epoch 51/100\n",
+      "280/280 [==============================] - 0s 75us/step - loss: 0.6377 - acc: 0.7071\n",
+      "Epoch 52/100\n",
+      "280/280 [==============================] - 0s 78us/step - loss: 0.6352 - acc: 0.7107\n",
+      "Epoch 53/100\n",
+      "280/280 [==============================] - 0s 75us/step - loss: 0.6326 - acc: 0.7107\n",
+      "Epoch 54/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.6299 - acc: 0.7286\n",
+      "Epoch 55/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.6273 - acc: 0.7214\n",
+      "Epoch 56/100\n",
+      "280/280 [==============================] - 0s 81us/step - loss: 0.6247 - acc: 0.7250\n",
+      "Epoch 57/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.6221 - acc: 0.7429\n",
+      "Epoch 58/100\n",
+      "280/280 [==============================] - 0s 73us/step - loss: 0.6193 - acc: 0.7500\n",
+      "Epoch 59/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.6166 - acc: 0.7571\n",
+      "Epoch 60/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.6137 - acc: 0.7714\n",
+      "Epoch 61/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.6107 - acc: 0.7679\n",
+      "Epoch 62/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.6077 - acc: 0.7786\n",
+      "Epoch 63/100\n",
+      "280/280 [==============================] - 0s 70us/step - loss: 0.6047 - acc: 0.7893\n",
+      "Epoch 64/100\n",
+      "280/280 [==============================] - 0s 68us/step - loss: 0.6016 - acc: 0.7893\n",
+      "Epoch 65/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.5985 - acc: 0.7929\n",
+      "Epoch 66/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5952 - acc: 0.8000\n",
+      "Epoch 67/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 76us/step - loss: 0.5920 - acc: 0.7964\n",
+      "Epoch 68/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.5889 - acc: 0.8036\n",
+      "Epoch 69/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.5857 - acc: 0.8000\n",
+      "Epoch 70/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.5825 - acc: 0.8071\n",
+      "Epoch 71/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.5792 - acc: 0.8071\n",
+      "Epoch 72/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5760 - acc: 0.8071\n",
+      "Epoch 73/100\n",
+      "280/280 [==============================] - 0s 95us/step - loss: 0.5726 - acc: 0.8143\n",
+      "Epoch 74/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.5693 - acc: 0.8143\n",
+      "Epoch 75/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5660 - acc: 0.8143\n",
+      "Epoch 76/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.5627 - acc: 0.8143\n",
+      "Epoch 77/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.5593 - acc: 0.8179\n",
+      "Epoch 78/100\n",
+      "280/280 [==============================] - 0s 84us/step - loss: 0.5557 - acc: 0.8179\n",
+      "Epoch 79/100\n",
+      "280/280 [==============================] - 0s 73us/step - loss: 0.5522 - acc: 0.8393\n",
+      "Epoch 80/100\n",
+      "280/280 [==============================] - 0s 78us/step - loss: 0.5487 - acc: 0.8321\n",
+      "Epoch 81/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5452 - acc: 0.8429\n",
+      "Epoch 82/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.5417 - acc: 0.8464\n",
+      "Epoch 83/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5382 - acc: 0.8464\n",
+      "Epoch 84/100\n",
+      "280/280 [==============================] - 0s 69us/step - loss: 0.5347 - acc: 0.8429\n",
+      "Epoch 85/100\n",
+      "280/280 [==============================] - 0s 73us/step - loss: 0.5312 - acc: 0.8500\n",
+      "Epoch 86/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.5278 - acc: 0.8536\n",
+      "Epoch 87/100\n",
+      "280/280 [==============================] - 0s 88us/step - loss: 0.5243 - acc: 0.8571\n",
+      "Epoch 88/100\n",
+      "280/280 [==============================] - 0s 78us/step - loss: 0.5208 - acc: 0.8571\n",
+      "Epoch 89/100\n",
+      "280/280 [==============================] - 0s 86us/step - loss: 0.5174 - acc: 0.8571\n",
+      "Epoch 90/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.5139 - acc: 0.8607\n",
+      "Epoch 91/100\n",
+      "280/280 [==============================] - 0s 78us/step - loss: 0.5105 - acc: 0.8643\n",
+      "Epoch 92/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.5072 - acc: 0.8714\n",
+      "Epoch 93/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.5039 - acc: 0.8714\n",
+      "Epoch 94/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.5003 - acc: 0.8714\n",
+      "Epoch 95/100\n",
+      "280/280 [==============================] - 0s 142us/step - loss: 0.4969 - acc: 0.8750\n",
+      "Epoch 96/100\n",
+      "280/280 [==============================] - 0s 104us/step - loss: 0.4933 - acc: 0.8750\n",
+      "Epoch 97/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.4899 - acc: 0.8750\n",
+      "Epoch 98/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.4866 - acc: 0.8714\n",
+      "Epoch 99/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.4836 - acc: 0.8714\n",
+      "Epoch 100/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.4804 - acc: 0.8750\n",
+      "70/70 [==============================] - 0s 3ms/step\n",
+      "Epoch 1/100\n",
+      "280/280 [==============================] - 1s 4ms/step - loss: 0.6613 - acc: 0.6929\n",
+      "Epoch 2/100\n",
+      "280/280 [==============================] - 0s 138us/step - loss: 0.6544 - acc: 0.7214\n",
+      "Epoch 3/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.6492 - acc: 0.7357\n",
+      "Epoch 4/100\n",
+      "280/280 [==============================] - 0s 81us/step - loss: 0.6440 - acc: 0.7250\n",
+      "Epoch 5/100\n",
+      "280/280 [==============================] - 0s 73us/step - loss: 0.6389 - acc: 0.7321\n",
+      "Epoch 6/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.6336 - acc: 0.7429\n",
+      "Epoch 7/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.6283 - acc: 0.7429\n",
+      "Epoch 8/100\n",
+      "280/280 [==============================] - 0s 68us/step - loss: 0.6229 - acc: 0.7679\n",
+      "Epoch 9/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6177 - acc: 0.7571\n",
+      "Epoch 10/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6121 - acc: 0.7714\n",
+      "Epoch 11/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.6066 - acc: 0.7714\n",
+      "Epoch 12/100\n",
+      "280/280 [==============================] - 0s 70us/step - loss: 0.6008 - acc: 0.7929\n",
+      "Epoch 13/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.5951 - acc: 0.8036\n",
+      "Epoch 14/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.5894 - acc: 0.8214\n",
+      "Epoch 15/100\n",
+      "280/280 [==============================] - 0s 69us/step - loss: 0.5839 - acc: 0.8250\n",
+      "Epoch 16/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.5782 - acc: 0.8321\n",
+      "Epoch 17/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5723 - acc: 0.8500\n",
+      "Epoch 18/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5664 - acc: 0.8500\n",
+      "Epoch 19/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5605 - acc: 0.8750\n",
+      "Epoch 20/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5541 - acc: 0.8821\n",
+      "Epoch 21/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5475 - acc: 0.9000\n",
+      "Epoch 22/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5411 - acc: 0.9000\n",
+      "Epoch 23/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.5345 - acc: 0.9071\n",
+      "Epoch 24/100\n",
+      "280/280 [==============================] - 0s 56us/step - loss: 0.5279 - acc: 0.9107\n",
+      "Epoch 25/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5212 - acc: 0.9071\n",
+      "Epoch 26/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5145 - acc: 0.9107\n",
+      "Epoch 27/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.5076 - acc: 0.9214\n",
+      "Epoch 28/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5007 - acc: 0.9179\n",
+      "Epoch 29/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4937 - acc: 0.9143\n",
+      "Epoch 30/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4867 - acc: 0.9179\n",
+      "Epoch 31/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4795 - acc: 0.9143\n",
+      "Epoch 32/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4725 - acc: 0.9143\n",
+      "Epoch 33/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.4655 - acc: 0.9286\n",
+      "Epoch 34/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.4587 - acc: 0.9286\n",
+      "Epoch 35/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4517 - acc: 0.9357\n",
+      "Epoch 36/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.4448 - acc: 0.9321\n",
+      "Epoch 37/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.4379 - acc: 0.9357\n",
+      "Epoch 38/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4310 - acc: 0.9321\n",
+      "Epoch 39/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4244 - acc: 0.9321\n",
+      "Epoch 40/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.4178 - acc: 0.9321\n",
+      "Epoch 41/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.4112 - acc: 0.9321\n",
+      "Epoch 42/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4048 - acc: 0.9321\n",
+      "Epoch 43/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3985 - acc: 0.9321\n",
+      "Epoch 44/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.3921 - acc: 0.9321\n",
+      "Epoch 45/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3860 - acc: 0.9321\n",
+      "Epoch 46/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.3799 - acc: 0.9321\n",
+      "Epoch 47/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.3742 - acc: 0.9321\n",
+      "Epoch 48/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.3682 - acc: 0.9321\n",
+      "Epoch 49/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3624 - acc: 0.9321\n",
+      "Epoch 50/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3567 - acc: 0.9321\n",
+      "Epoch 51/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3512 - acc: 0.9286\n",
+      "Epoch 52/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3458 - acc: 0.9321\n",
+      "Epoch 53/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3407 - acc: 0.9321\n",
+      "Epoch 54/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3355 - acc: 0.9321\n",
+      "Epoch 55/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.3304 - acc: 0.9286\n",
+      "Epoch 56/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3252 - acc: 0.9357\n",
+      "Epoch 57/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3201 - acc: 0.9286\n",
+      "Epoch 58/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3152 - acc: 0.9321\n",
+      "Epoch 59/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3102 - acc: 0.9429\n",
+      "Epoch 60/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3055 - acc: 0.9321\n",
+      "Epoch 61/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3011 - acc: 0.9357\n",
+      "Epoch 62/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2967 - acc: 0.9393\n",
+      "Epoch 63/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.2922 - acc: 0.9429\n",
+      "Epoch 64/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2877 - acc: 0.9464\n",
+      "Epoch 65/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2832 - acc: 0.9536\n",
+      "Epoch 66/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2788 - acc: 0.9536\n",
+      "Epoch 67/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2749 - acc: 0.9500\n",
+      "Epoch 68/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2708 - acc: 0.9536\n",
+      "Epoch 69/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2668 - acc: 0.9536\n",
+      "Epoch 70/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2632 - acc: 0.9571\n",
+      "Epoch 71/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2592 - acc: 0.9607\n",
+      "Epoch 72/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.2555 - acc: 0.9536\n",
+      "Epoch 73/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2518 - acc: 0.9607\n",
+      "Epoch 74/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2484 - acc: 0.9571\n",
+      "Epoch 75/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.2451 - acc: 0.9607\n",
+      "Epoch 76/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2420 - acc: 0.9607\n",
+      "Epoch 77/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.2385 - acc: 0.9607\n",
+      "Epoch 78/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2352 - acc: 0.9607\n",
+      "Epoch 79/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2320 - acc: 0.9607\n",
+      "Epoch 80/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2289 - acc: 0.9643\n",
+      "Epoch 81/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.2258 - acc: 0.9643\n",
+      "Epoch 82/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2230 - acc: 0.9679\n",
+      "Epoch 83/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.2200 - acc: 0.9643\n",
+      "Epoch 84/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.2169 - acc: 0.9679\n",
+      "Epoch 85/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2141 - acc: 0.9643\n",
+      "Epoch 86/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2113 - acc: 0.9679\n",
+      "Epoch 87/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.2086 - acc: 0.9679\n",
+      "Epoch 88/100\n",
+      "280/280 [==============================] - 0s 56us/step - loss: 0.2057 - acc: 0.9679\n",
+      "Epoch 89/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2036 - acc: 0.9679\n",
+      "Epoch 90/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.2009 - acc: 0.9679\n",
+      "Epoch 91/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.1983 - acc: 0.9679\n",
+      "Epoch 92/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.1958 - acc: 0.9679\n",
+      "Epoch 93/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.1935 - acc: 0.9714\n",
+      "Epoch 94/100\n",
+      "280/280 [==============================] - 0s 56us/step - loss: 0.1909 - acc: 0.9750\n",
+      "Epoch 95/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.1889 - acc: 0.9714\n",
+      "Epoch 96/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.1867 - acc: 0.9750\n",
+      "Epoch 97/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.1844 - acc: 0.9714\n",
+      "Epoch 98/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.1821 - acc: 0.9750\n",
+      "Epoch 99/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.1798 - acc: 0.9714\n",
+      "Epoch 100/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.1777 - acc: 0.9750\n",
+      "70/70 [==============================] - 0s 3ms/step\n",
+      "Epoch 1/100\n",
+      "280/280 [==============================] - 1s 3ms/step - loss: 0.7067 - acc: 0.4179\n",
+      "Epoch 2/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.7000 - acc: 0.4214\n",
+      "Epoch 3/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6954 - acc: 0.3929\n",
+      "Epoch 4/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6917 - acc: 0.3964\n",
+      "Epoch 5/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6882 - acc: 0.4036\n",
+      "Epoch 6/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6849 - acc: 0.4000\n",
+      "Epoch 7/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6815 - acc: 0.4250\n",
+      "Epoch 8/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6783 - acc: 0.4750\n",
+      "Epoch 9/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6751 - acc: 0.5250\n",
+      "Epoch 10/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6717 - acc: 0.5714\n",
+      "Epoch 11/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6684 - acc: 0.5929\n",
+      "Epoch 12/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6649 - acc: 0.6071\n",
+      "Epoch 13/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6613 - acc: 0.6179\n",
+      "Epoch 14/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6575 - acc: 0.6464\n",
+      "Epoch 15/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6535 - acc: 0.6607\n",
+      "Epoch 16/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6494 - acc: 0.6750\n",
+      "Epoch 17/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6451 - acc: 0.6714\n",
+      "Epoch 18/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.6407 - acc: 0.6929\n",
+      "Epoch 19/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6362 - acc: 0.7036\n",
+      "Epoch 20/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.6316 - acc: 0.7143\n",
+      "Epoch 21/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6268 - acc: 0.7286\n",
+      "Epoch 22/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.6218 - acc: 0.7464\n",
+      "Epoch 23/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6167 - acc: 0.7536\n",
+      "Epoch 24/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6114 - acc: 0.7643\n",
+      "Epoch 25/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.6059 - acc: 0.7714\n",
+      "Epoch 26/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.6001 - acc: 0.7929\n",
+      "Epoch 27/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5945 - acc: 0.8036\n",
+      "Epoch 28/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5887 - acc: 0.8179\n",
+      "Epoch 29/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5827 - acc: 0.8321\n",
+      "Epoch 30/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5765 - acc: 0.8393\n",
+      "Epoch 31/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5700 - acc: 0.8393\n",
+      "Epoch 32/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5634 - acc: 0.8429\n",
+      "Epoch 33/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5570 - acc: 0.8464\n",
+      "Epoch 34/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5505 - acc: 0.8536\n",
+      "Epoch 35/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5442 - acc: 0.8500\n",
+      "Epoch 36/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5379 - acc: 0.8464\n",
+      "Epoch 37/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5317 - acc: 0.8464\n",
+      "Epoch 38/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5252 - acc: 0.8500\n",
+      "Epoch 39/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5187 - acc: 0.8536\n",
+      "Epoch 40/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5120 - acc: 0.8643\n",
+      "Epoch 41/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5053 - acc: 0.8643\n",
+      "Epoch 42/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4983 - acc: 0.8714\n",
+      "Epoch 43/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4916 - acc: 0.8750\n",
+      "Epoch 44/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4847 - acc: 0.8786\n",
+      "Epoch 45/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4782 - acc: 0.8821\n",
+      "Epoch 46/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4716 - acc: 0.8893\n",
+      "Epoch 47/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.4650 - acc: 0.8893\n",
+      "Epoch 48/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4586 - acc: 0.8893\n",
+      "Epoch 49/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.4524 - acc: 0.9036\n",
+      "Epoch 50/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4461 - acc: 0.9000\n",
+      "Epoch 51/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.4399 - acc: 0.9000\n",
+      "Epoch 52/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4335 - acc: 0.9000\n",
+      "Epoch 53/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.4273 - acc: 0.9036\n",
+      "Epoch 54/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4213 - acc: 0.9071\n",
+      "Epoch 55/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4154 - acc: 0.9179\n",
+      "Epoch 56/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4095 - acc: 0.9143\n",
+      "Epoch 57/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.4038 - acc: 0.9214\n",
+      "Epoch 58/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3983 - acc: 0.9214\n",
+      "Epoch 59/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3925 - acc: 0.9250\n",
+      "Epoch 60/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3868 - acc: 0.9250\n",
+      "Epoch 61/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3810 - acc: 0.9357\n",
+      "Epoch 62/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3755 - acc: 0.9321\n",
+      "Epoch 63/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3703 - acc: 0.9429\n",
+      "Epoch 64/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3650 - acc: 0.9500\n",
+      "Epoch 65/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3602 - acc: 0.9357\n",
+      "Epoch 66/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3553 - acc: 0.9429\n",
+      "Epoch 67/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3506 - acc: 0.9536\n",
+      "Epoch 68/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3462 - acc: 0.9464\n",
+      "Epoch 69/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3418 - acc: 0.9464\n",
+      "Epoch 70/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.3375 - acc: 0.9500\n",
+      "Epoch 71/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3331 - acc: 0.9536\n",
+      "Epoch 72/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3288 - acc: 0.9536\n",
+      "Epoch 73/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3244 - acc: 0.9571\n",
+      "Epoch 74/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.3202 - acc: 0.9643\n",
+      "Epoch 75/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3159 - acc: 0.9607\n",
+      "Epoch 76/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3119 - acc: 0.9607\n",
+      "Epoch 77/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.3080 - acc: 0.9607\n",
+      "Epoch 78/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3038 - acc: 0.9607\n",
+      "Epoch 79/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.3001 - acc: 0.9607\n",
+      "Epoch 80/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.2963 - acc: 0.9607\n",
+      "Epoch 81/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2925 - acc: 0.9571\n",
+      "Epoch 82/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.2888 - acc: 0.9643\n",
+      "Epoch 83/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2852 - acc: 0.9643\n",
+      "Epoch 84/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2815 - acc: 0.9679\n",
+      "Epoch 85/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2782 - acc: 0.9643\n",
+      "Epoch 86/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.2747 - acc: 0.9643\n",
+      "Epoch 87/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2716 - acc: 0.9643\n",
+      "Epoch 88/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.2682 - acc: 0.9679\n",
+      "Epoch 89/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.2651 - acc: 0.9679\n",
+      "Epoch 90/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.2620 - acc: 0.9679\n",
+      "Epoch 91/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2592 - acc: 0.9679\n",
+      "Epoch 92/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.2561 - acc: 0.9679\n",
+      "Epoch 93/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.2533 - acc: 0.9714\n",
+      "Epoch 94/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.2504 - acc: 0.9714\n",
+      "Epoch 95/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.2474 - acc: 0.9714\n",
+      "Epoch 96/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2449 - acc: 0.9714\n",
+      "Epoch 97/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2424 - acc: 0.9679\n",
+      "Epoch 98/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.2396 - acc: 0.9714\n",
+      "Epoch 99/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.2371 - acc: 0.9750\n",
+      "Epoch 100/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.2348 - acc: 0.9714\n",
+      "70/70 [==============================] - 0s 3ms/step\n",
+      "Epoch 1/100\n",
+      "280/280 [==============================] - 1s 4ms/step - loss: 0.6880 - acc: 0.5214\n",
+      "Epoch 2/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.6785 - acc: 0.5429\n",
+      "Epoch 3/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.6711 - acc: 0.5679\n",
+      "Epoch 4/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.6646 - acc: 0.6214\n",
+      "Epoch 5/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.6586 - acc: 0.6429\n",
+      "Epoch 6/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.6525 - acc: 0.6714\n",
+      "Epoch 7/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.6468 - acc: 0.6821\n",
+      "Epoch 8/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.6413 - acc: 0.6929\n",
+      "Epoch 9/100\n",
+      "280/280 [==============================] - 0s 82us/step - loss: 0.6358 - acc: 0.7107\n",
+      "Epoch 10/100\n",
+      "280/280 [==============================] - 0s 100us/step - loss: 0.6304 - acc: 0.7393\n",
+      "Epoch 11/100\n",
+      "280/280 [==============================] - 0s 93us/step - loss: 0.6249 - acc: 0.7607\n",
+      "Epoch 12/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6196 - acc: 0.7750\n",
+      "Epoch 13/100\n",
+      "280/280 [==============================] - 0s 89us/step - loss: 0.6144 - acc: 0.7929\n",
+      "Epoch 14/100\n",
+      "280/280 [==============================] - 0s 94us/step - loss: 0.6095 - acc: 0.8000\n",
+      "Epoch 15/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.6048 - acc: 0.8143\n",
+      "Epoch 16/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 73us/step - loss: 0.6001 - acc: 0.8143\n",
+      "Epoch 17/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5954 - acc: 0.8214\n",
+      "Epoch 18/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5906 - acc: 0.8250\n",
+      "Epoch 19/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.5860 - acc: 0.8179\n",
+      "Epoch 20/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.5814 - acc: 0.8250\n",
+      "Epoch 21/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.5769 - acc: 0.8250\n",
+      "Epoch 22/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5724 - acc: 0.8214\n",
+      "Epoch 23/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.5680 - acc: 0.8179\n",
+      "Epoch 24/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.5634 - acc: 0.8107\n",
+      "Epoch 25/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.5590 - acc: 0.8143\n",
+      "Epoch 26/100\n",
+      "280/280 [==============================] - 0s 96us/step - loss: 0.5550 - acc: 0.8107\n",
+      "Epoch 27/100\n",
+      "280/280 [==============================] - ETA: 0s - loss: 0.5588 - acc: 0.750 - 0s 79us/step - loss: 0.5508 - acc: 0.8071\n",
+      "Epoch 28/100\n",
+      "280/280 [==============================] - 0s 85us/step - loss: 0.5466 - acc: 0.8036\n",
+      "Epoch 29/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.5425 - acc: 0.8071\n",
+      "Epoch 30/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.5382 - acc: 0.8107\n",
+      "Epoch 31/100\n",
+      "280/280 [==============================] - 0s 75us/step - loss: 0.5341 - acc: 0.8071\n",
+      "Epoch 32/100\n",
+      "280/280 [==============================] - 0s 68us/step - loss: 0.5300 - acc: 0.8071\n",
+      "Epoch 33/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.5259 - acc: 0.8071\n",
+      "Epoch 34/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5218 - acc: 0.8071\n",
+      "Epoch 35/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.5176 - acc: 0.8107\n",
+      "Epoch 36/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.5133 - acc: 0.8143\n",
+      "Epoch 37/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5091 - acc: 0.8143\n",
+      "Epoch 38/100\n",
+      "280/280 [==============================] - 0s 63us/step - loss: 0.5050 - acc: 0.8107\n",
+      "Epoch 39/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.5008 - acc: 0.8107\n",
+      "Epoch 40/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.4970 - acc: 0.8143\n",
+      "Epoch 41/100\n",
+      "280/280 [==============================] - 0s 76us/step - loss: 0.4929 - acc: 0.8143\n",
+      "Epoch 42/100\n",
+      "280/280 [==============================] - 0s 102us/step - loss: 0.4890 - acc: 0.8179\n",
+      "Epoch 43/100\n",
+      "280/280 [==============================] - 0s 104us/step - loss: 0.4850 - acc: 0.8107\n",
+      "Epoch 44/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.4813 - acc: 0.8107\n",
+      "Epoch 45/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.4776 - acc: 0.8143\n",
+      "Epoch 46/100\n",
+      "280/280 [==============================] - 0s 81us/step - loss: 0.4741 - acc: 0.8143\n",
+      "Epoch 47/100\n",
+      "280/280 [==============================] - 0s 91us/step - loss: 0.4706 - acc: 0.8107\n",
+      "Epoch 48/100\n",
+      "280/280 [==============================] - 0s 77us/step - loss: 0.4669 - acc: 0.8107\n",
+      "Epoch 49/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4633 - acc: 0.8143\n",
+      "Epoch 50/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.4597 - acc: 0.8250\n",
+      "Epoch 51/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.4562 - acc: 0.8321\n",
+      "Epoch 52/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.4529 - acc: 0.8286\n",
+      "Epoch 53/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4493 - acc: 0.8250\n",
+      "Epoch 54/100\n",
+      "280/280 [==============================] - 0s 69us/step - loss: 0.4458 - acc: 0.8321\n",
+      "Epoch 55/100\n",
+      "280/280 [==============================] - 0s 65us/step - loss: 0.4421 - acc: 0.8321\n",
+      "Epoch 56/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.4385 - acc: 0.8393\n",
+      "Epoch 57/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.4348 - acc: 0.8393\n",
+      "Epoch 58/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.4313 - acc: 0.8464\n",
+      "Epoch 59/100\n",
+      "280/280 [==============================] - 0s 66us/step - loss: 0.4278 - acc: 0.8464\n",
+      "Epoch 60/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.4244 - acc: 0.8500\n",
+      "Epoch 61/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4214 - acc: 0.8429\n",
+      "Epoch 62/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.4188 - acc: 0.8500\n",
+      "Epoch 63/100\n",
+      "280/280 [==============================] - 0s 64us/step - loss: 0.4156 - acc: 0.8536\n",
+      "Epoch 64/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.4130 - acc: 0.8571\n",
+      "Epoch 65/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.4104 - acc: 0.8571\n",
+      "Epoch 66/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.4075 - acc: 0.8571\n",
+      "Epoch 67/100\n",
+      "280/280 [==============================] - 0s 90us/step - loss: 0.4048 - acc: 0.8607\n",
+      "Epoch 68/100\n",
+      "280/280 [==============================] - 0s 62us/step - loss: 0.4021 - acc: 0.8607\n",
+      "Epoch 69/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.3992 - acc: 0.8643\n",
+      "Epoch 70/100\n",
+      "280/280 [==============================] - 0s 66us/step - loss: 0.3962 - acc: 0.8643\n",
+      "Epoch 71/100\n",
+      "280/280 [==============================] - 0s 58us/step - loss: 0.3936 - acc: 0.8643\n",
+      "Epoch 72/100\n",
+      "280/280 [==============================] - 0s 57us/step - loss: 0.3904 - acc: 0.8679\n",
+      "Epoch 73/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3877 - acc: 0.8643\n",
+      "Epoch 74/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3850 - acc: 0.8607\n",
+      "Epoch 75/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3824 - acc: 0.8643\n",
+      "Epoch 76/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3798 - acc: 0.8750\n",
+      "Epoch 77/100\n",
+      "280/280 [==============================] - 0s 66us/step - loss: 0.3773 - acc: 0.8679\n",
+      "Epoch 78/100\n",
+      "280/280 [==============================] - 0s 59us/step - loss: 0.3750 - acc: 0.8714\n",
+      "Epoch 79/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.3723 - acc: 0.8714\n",
+      "Epoch 80/100\n",
+      "280/280 [==============================] - 0s 69us/step - loss: 0.3698 - acc: 0.8679\n",
+      "Epoch 81/100\n",
+      "280/280 [==============================] - 0s 68us/step - loss: 0.3671 - acc: 0.8714\n",
+      "Epoch 82/100\n",
+      "280/280 [==============================] - 0s 68us/step - loss: 0.3647 - acc: 0.8786\n",
+      "Epoch 83/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.3627 - acc: 0.8786\n",
+      "Epoch 84/100\n",
+      "280/280 [==============================] - 0s 74us/step - loss: 0.3602 - acc: 0.8786\n",
+      "Epoch 85/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.3579 - acc: 0.8786\n",
+      "Epoch 86/100\n",
+      "280/280 [==============================] - 0s 97us/step - loss: 0.3556 - acc: 0.8821\n",
+      "Epoch 87/100\n",
+      "280/280 [==============================] - 0s 80us/step - loss: 0.3535 - acc: 0.8821\n",
+      "Epoch 88/100\n",
+      "280/280 [==============================] - 0s 79us/step - loss: 0.3513 - acc: 0.8821\n",
+      "Epoch 89/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.3490 - acc: 0.8786\n",
+      "Epoch 90/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.3468 - acc: 0.8786\n",
+      "Epoch 91/100\n",
+      "280/280 [==============================] - 0s 83us/step - loss: 0.3445 - acc: 0.8893\n",
+      "Epoch 92/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.3424 - acc: 0.8857\n",
+      "Epoch 93/100\n",
+      "280/280 [==============================] - 0s 72us/step - loss: 0.3402 - acc: 0.8857\n",
+      "Epoch 94/100\n",
+      "280/280 [==============================] - 0s 67us/step - loss: 0.3382 - acc: 0.8929\n",
+      "Epoch 95/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.3358 - acc: 0.8929\n",
+      "Epoch 96/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3339 - acc: 0.8929\n",
+      "Epoch 97/100\n",
+      "280/280 [==============================] - 0s 61us/step - loss: 0.3320 - acc: 0.8929\n",
+      "Epoch 98/100\n",
+      "280/280 [==============================] - 0s 60us/step - loss: 0.3304 - acc: 0.8929\n",
+      "Epoch 99/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "280/280 [==============================] - 0s 62us/step - loss: 0.3281 - acc: 0.8964\n",
+      "Epoch 100/100\n",
+      "280/280 [==============================] - 0s 71us/step - loss: 0.3263 - acc: 0.9000\n",
+      "70/70 [==============================] - 0s 4ms/step\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "'\\ndef plot_points(features_2d, plt=plt, marker=\\'o\\'):\\n    colors = [[\"steelblue\", \"chocolate\"][i] for i in labels]\\n    plt.scatter(features_2d.iloc[:, 0], features_2d.iloc[:, 1], color=colors, marker=marker);\\n\\ndef train_and_plot_decision_surface(\\n    name, classifier, features_2d, labels, preproc=None, plt=plt, marker=\\'o\\', N=400\\n):\\n\\n    features_2d = np.array(features_2d)\\n    xmin, ymin = features_2d.min(axis=0)\\n    xmax, ymax = features_2d.max(axis=0)\\n\\n    x = np.linspace(xmin, xmax, N)\\n    y = np.linspace(ymin, ymax, N)\\n    points = np.array(np.meshgrid(x, y)).T.reshape(-1, 2)\\n\\n    if preproc is not None:\\n        points_for_classifier = preproc.fit_transform(points)\\n        features_2d = preproc.fit_transform(features_2d)\\n    else:\\n        points_for_classifier = points\\n\\n    classifier.fit(features_2d, labels, epochs=20)\\n    predicted = classifier.predict(features_2d)\\n    print(predicted)\\n    if preproc is not None:\\n        name += \" (w/ preprocessing)\"\\n    print(name + \":\\t\", sum(predicted == labels), \"/\", len(labels), \"correct\")\\n\\n    classes = np.array(classifier.predict(points_for_classifier), dtype=bool)\\n    plt.plot(\\n        points[~classes][:, 0],\\n        points[~classes][:, 1],\\n        color=\"steelblue\",\\n        marker=marker,\\n        markersize=1,\\n        alpha=0.01,\\n    )\\n    plt.plot(\\n        points[classes][:, 0],\\n        points[classes][:, 1],\\n        color=\"chocolate\",\\n        marker=marker,\\n        markersize=1,\\n        alpha=0.01,\\n    )\\n    \\n_, ax = plt.subplots(figsize=(6, 6))\\n    \\ntrain_and_plot_decision_surface(\"Neural Net\", model, features, labels, plt=ax)\\n\\nplot_points(plt=ax)\\n'"
+       "0.9085714285714287"
       ]
      },
-     "execution_count": 132,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "\"\"\"\n",
-    "def plot_points(features_2d, plt=plt, marker='o'):\n",
-    "    colors = [[\"steelblue\", \"chocolate\"][i] for i in labels]\n",
-    "    plt.scatter(features_2d.iloc[:, 0], features_2d.iloc[:, 1], color=colors, marker=marker);\n",
-    "\n",
-    "def train_and_plot_decision_surface(\n",
-    "    name, classifier, features_2d, labels, preproc=None, plt=plt, marker='o', N=400\n",
-    "):\n",
-    "\n",
-    "    features_2d = np.array(features_2d)\n",
-    "    xmin, ymin = features_2d.min(axis=0)\n",
-    "    xmax, ymax = features_2d.max(axis=0)\n",
-    "\n",
-    "    x = np.linspace(xmin, xmax, N)\n",
-    "    y = np.linspace(ymin, ymax, N)\n",
-    "    points = np.array(np.meshgrid(x, y)).T.reshape(-1, 2)\n",
-    "\n",
-    "    if preproc is not None:\n",
-    "        points_for_classifier = preproc.fit_transform(points)\n",
-    "        features_2d = preproc.fit_transform(features_2d)\n",
-    "    else:\n",
-    "        points_for_classifier = points\n",
-    "\n",
-    "    classifier.fit(features_2d, labels, epochs=20)\n",
-    "    predicted = classifier.predict(features_2d)\n",
-    "    print(predicted)\n",
-    "    if preproc is not None:\n",
-    "        name += \" (w/ preprocessing)\"\n",
-    "    print(name + \":\\t\", sum(predicted == labels), \"/\", len(labels), \"correct\")\n",
-    "\n",
-    "    classes = np.array(classifier.predict(points_for_classifier), dtype=bool)\n",
-    "    plt.plot(\n",
-    "        points[~classes][:, 0],\n",
-    "        points[~classes][:, 1],\n",
-    "        color=\"steelblue\",\n",
-    "        marker=marker,\n",
-    "        markersize=1,\n",
-    "        alpha=0.01,\n",
-    "    )\n",
-    "    plt.plot(\n",
-    "        points[classes][:, 0],\n",
-    "        points[classes][:, 1],\n",
-    "        color=\"chocolate\",\n",
-    "        marker=marker,\n",
-    "        markersize=1,\n",
-    "        alpha=0.01,\n",
-    "    )\n",
-    "    \n",
-    "_, ax = plt.subplots(figsize=(6, 6))\n",
-    "    \n",
-    "train_and_plot_decision_surface(\"Neural Net\", model, features, labels, plt=ax)\n",
-    "\n",
-    "plot_points(plt=ax)\n",
-    "\"\"\""
+    "# We wrap the Keras model we created above with KerasClassifier\n",
+    "from keras.wrappers.scikit_learn import KerasClassifier \n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "model_scikit = KerasClassifier(build_fn=a_simple_NN, epochs=num_epochs)\n",
+    "cross_validation = cross_val_score(model_scikit, X_train, y_train, cv=5)\n",
+    "np.mean(cross_validation)"
    ]
   },
   {
@@ -1318,13 +2547,7 @@
       "157/157 [==============================] - 0s 128us/step - loss: 0.6070 - acc: 0.6242 - val_loss: 0.6018 - val_acc: 0.6029\n",
       "Epoch 59/1000\n",
       "157/157 [==============================] - 0s 165us/step - loss: 0.6057 - acc: 0.6242 - val_loss: 0.6001 - val_acc: 0.6029\n",
-      "Epoch 60/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 60/1000\n",
       "157/157 [==============================] - 0s 263us/step - loss: 0.6039 - acc: 0.6242 - val_loss: 0.5982 - val_acc: 0.6176\n",
       "Epoch 61/1000\n",
       "157/157 [==============================] - 0s 244us/step - loss: 0.6023 - acc: 0.6242 - val_loss: 0.5963 - val_acc: 0.6176\n",
@@ -1568,13 +2791,7 @@
       "157/157 [==============================] - 0s 191us/step - loss: 0.3540 - acc: 0.9236 - val_loss: 0.3205 - val_acc: 0.8971\n",
       "Epoch 178/1000\n",
       "157/157 [==============================] - 0s 374us/step - loss: 0.3529 - acc: 0.9108 - val_loss: 0.3181 - val_acc: 0.8971\n",
-      "Epoch 179/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 179/1000\n",
       "157/157 [==============================] - 0s 307us/step - loss: 0.3500 - acc: 0.9236 - val_loss: 0.3156 - val_acc: 0.8971\n",
       "Epoch 180/1000\n",
       "157/157 [==============================] - 0s 319us/step - loss: 0.3485 - acc: 0.9236 - val_loss: 0.3136 - val_acc: 0.8971\n",
@@ -1816,13 +3033,7 @@
       "157/157 [==============================] - 0s 155us/step - loss: 0.2019 - acc: 0.9618 - val_loss: 0.1799 - val_acc: 0.9118\n",
       "Epoch 296/1000\n",
       "157/157 [==============================] - 0s 165us/step - loss: 0.1995 - acc: 0.9554 - val_loss: 0.1778 - val_acc: 0.9118\n",
-      "Epoch 297/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 297/1000\n",
       "157/157 [==============================] - 0s 165us/step - loss: 0.1990 - acc: 0.9618 - val_loss: 0.1810 - val_acc: 0.9118\n",
       "Epoch 298/1000\n",
       "157/157 [==============================] - 0s 189us/step - loss: 0.1975 - acc: 0.9618 - val_loss: 0.1822 - val_acc: 0.9118\n",
@@ -2064,13 +3275,7 @@
       "157/157 [==============================] - 0s 175us/step - loss: 0.1374 - acc: 0.9682 - val_loss: 0.1359 - val_acc: 0.9118\n",
       "Epoch 414/1000\n",
       "157/157 [==============================] - 0s 171us/step - loss: 0.1346 - acc: 0.9682 - val_loss: 0.1370 - val_acc: 0.9118\n",
-      "Epoch 415/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 415/1000\n",
       "157/157 [==============================] - 0s 188us/step - loss: 0.1352 - acc: 0.9682 - val_loss: 0.1363 - val_acc: 0.9118\n",
       "Epoch 416/1000\n",
       "157/157 [==============================] - 0s 130us/step - loss: 0.1364 - acc: 0.9745 - val_loss: 0.1368 - val_acc: 0.9118\n",
@@ -2310,13 +3515,7 @@
       "157/157 [==============================] - 0s 340us/step - loss: 0.0972 - acc: 0.9809 - val_loss: 0.1201 - val_acc: 0.9118\n",
       "Epoch 531/1000\n",
       "157/157 [==============================] - 0s 277us/step - loss: 0.0994 - acc: 0.9745 - val_loss: 0.1132 - val_acc: 0.9412\n",
-      "Epoch 532/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 532/1000\n",
       "157/157 [==============================] - 0s 287us/step - loss: 0.0974 - acc: 0.9745 - val_loss: 0.1083 - val_acc: 0.9559\n",
       "Epoch 533/1000\n",
       "157/157 [==============================] - 0s 209us/step - loss: 0.0983 - acc: 0.9809 - val_loss: 0.1158 - val_acc: 0.9265\n",
@@ -2558,13 +3757,7 @@
       "157/157 [==============================] - 0s 146us/step - loss: 0.0754 - acc: 0.9745 - val_loss: 0.0966 - val_acc: 0.9559\n",
       "Epoch 649/1000\n",
       "157/157 [==============================] - 0s 142us/step - loss: 0.0736 - acc: 0.9873 - val_loss: 0.1073 - val_acc: 0.9559\n",
-      "Epoch 650/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 650/1000\n",
       "157/157 [==============================] - 0s 119us/step - loss: 0.0754 - acc: 0.9809 - val_loss: 0.0996 - val_acc: 0.9559\n",
       "Epoch 651/1000\n",
       "157/157 [==============================] - 0s 125us/step - loss: 0.0730 - acc: 0.9873 - val_loss: 0.1035 - val_acc: 0.9559\n",
@@ -2806,13 +3999,7 @@
       "157/157 [==============================] - 0s 200us/step - loss: 0.0588 - acc: 0.9936 - val_loss: 0.0994 - val_acc: 0.9559\n",
       "Epoch 767/1000\n",
       "157/157 [==============================] - 0s 249us/step - loss: 0.0592 - acc: 0.9936 - val_loss: 0.0977 - val_acc: 0.9559\n",
-      "Epoch 768/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 768/1000\n",
       "157/157 [==============================] - 0s 222us/step - loss: 0.0583 - acc: 0.9809 - val_loss: 0.0848 - val_acc: 0.9706\n",
       "Epoch 769/1000\n",
       "157/157 [==============================] - 0s 163us/step - loss: 0.0591 - acc: 0.9936 - val_loss: 0.0839 - val_acc: 0.9706\n",
@@ -3054,13 +4241,7 @@
       "157/157 [==============================] - 0s 122us/step - loss: 0.0473 - acc: 0.9936 - val_loss: 0.0863 - val_acc: 0.9706\n",
       "Epoch 885/1000\n",
       "157/157 [==============================] - 0s 152us/step - loss: 0.0469 - acc: 0.9873 - val_loss: 0.0787 - val_acc: 0.9706\n",
-      "Epoch 886/1000\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "Epoch 886/1000\n",
       "157/157 [==============================] - 0s 161us/step - loss: 0.0477 - acc: 0.9936 - val_loss: 0.0853 - val_acc: 0.9706\n",
       "Epoch 887/1000\n",
       "157/157 [==============================] - 0s 176us/step - loss: 0.0475 - acc: 0.9936 - val_loss: 0.0957 - val_acc: 0.9559\n",
@@ -3415,7 +4596,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.0"
+   "version": "3.6.8"
   },
   "latex_envs": {
    "LaTeX_envs_menu_present": true,
-- 
GitLab