{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<script>\n",
       "  var password,\n",
       "      teacher_mode,\n",
       "      isHtml;\n",
       "      \n",
       "  var class_output,\n",
       "      class_input,\n",
       "      class_answer;\n",
       "      \n",
       "  function code_toggle(e) {\n",
       "    var orig_e = e;\n",
       "    while (!e.closest(class_output).previousElementSibling.classList.contains(class_input)) {\n",
       "      e = e.closest(class_output).previousElementSibling;\n",
       "    }\n",
       "    var target = e.closest(class_output).previousElementSibling;\n",
       "    if (target.getAttribute(\"style\") == \"\" || target.getAttribute(\"style\") == null) {\n",
       "      target.style.display = \"none\";\n",
       "      orig_e.innerHTML = 'show code';\n",
       "    }\n",
       "    else {\n",
       "      target.style.removeProperty(\"display\");\n",
       "      orig_e.innerHTML = 'hide code';\n",
       "    }\n",
       "  }\n",
       "  \n",
       "  function hide_answer(e) {\n",
       "    var target = e.closest(class_answer).nextElementSibling;\n",
       "    //e.closest(class_output).previousElementSibling.style.display = \"none\";\n",
       "    if (target.getAttribute(\"style\") == \"\" || target.getAttribute(\"style\") == null) {\n",
       "      target.style.display = \"none\";\n",
       "      e.innerHTML = 'show answer';\n",
       "    }\n",
       "    else if (teacher_mode) {\n",
       "        e.innerHTML = 'hide answer';\n",
       "        target.style.removeProperty(\"display\");\n",
       "    }\n",
       "  }\n",
       "  \n",
       "  function done() { \n",
       "    document.getElementById(\"popup\").style.display = \"none\";\n",
       "    var input = document.getElementById(\"password\").value;\n",
       "    if (input==password) { teacher_mode=1; alert(\"Unlocked!\");}\n",
       "    else { teacher_mode=0; alert(\"Wrong password!\");}       \n",
       "  };\n",
       "\n",
       "  function unlock() {\n",
       "    document.getElementById(\"popup\").style.display = \"block\";\n",
       "  }\n",
       "  \n",
       "  $(document).ready(function() {\n",
       "    $.ajax({\n",
       "      type: \"GET\",  \n",
       "      url: \"https://raw.githubusercontent.com/ming-zhao/ming-zhao.github.io/master/data/course.csv\",\n",
       "      dataType: \"text\",       \n",
       "      success: function(data)  \n",
       "      {\n",
       "        var items = data.split(',');\n",
       "        var url = window.location.pathname;\n",
       "        var filename = url.substring(url.lastIndexOf('/')+1);\n",
       "        password='123';\n",
       "        for (var i = 0, len = items.length; i < len; ++i) {\n",
       "            if (filename.includes(items[i].trim()) && i%2==0 && i<items.length) {\n",
       "                password=items[i+1].trim();\n",
       "                break;\n",
       "            }\n",
       "        }\n",
       "        var code_blocks = document.getElementsByClassName('nbinput docutils container');\n",
       "        if (code_blocks[0]==null) { \n",
       "            isHtml=0;\n",
       "            code_blocks = document.getElementsByClassName('input');\n",
       "            class_output=\".output_wrapper\";\n",
       "            class_input=\"input\";\n",
       "            class_answer='.cell';\n",
       "        }\n",
       "        else { \n",
       "            isHtml=1;\n",
       "            class_output=\".nboutput\";\n",
       "            class_input=\"nbinput\";\n",
       "            class_answer=\".nboutput\";\n",
       "        }\n",
       "        \n",
       "        for (var i = 0, len = code_blocks.length; i < len; ++i) {\n",
       "          if (\n",
       "              code_blocks[i].innerHTML.indexOf(\"toggle\") !== -1 \n",
       "              || code_blocks[i].innerHTML.indexOf(\"button onclick\") !== -1\n",
       "             ) {\n",
       "            code_blocks[i].style.display = \"none\";\n",
       "          }\n",
       "        }\n",
       "        for (var i = 0, len = code_blocks.length; i < len; ++i) {\n",
       "          if (code_blocks[i].innerHTML.indexOf(\"hide_answer\") !== -1) {\n",
       "            code_blocks[i].style.display = \"none\";\n",
       "            if (isHtml) {\n",
       "              code_blocks[i].nextElementSibling.nextElementSibling.style.display = \"none\";\n",
       "            }\n",
       "            else{\n",
       "              code_blocks[i].closest(class_answer).nextElementSibling.style.display = \"none\";\n",
       "            }            \n",
       "          }\n",
       "        }\n",
       "      }\n",
       "    });\n",
       "  });\n",
       "</script>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<div id=\"popup\" style=\"padding-bottom:5px; display:none;\">\n",
       "    <div>Enter Password:</div>\n",
       "    <input id=\"password\" type=\"password\"/>\n",
       "    <button onclick=\"done()\" style=\"border-radius: 12px;\">Submit</button>    \n",
       "</div>\n",
       "<button onclick=\"unlock()\" style=\"border-radius: 12px;\">Unclock</button>\n",
       "<a href=\"#\" onclick=\"code_toggle(this); return false;\">show code</a>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%run ../initscript.py\n",
    "HTML(\"\"\"\n",
    "<div id=\"popup\" style=\"padding-bottom:5px; display:none;\">\n",
    "    <div>Enter Password:</div>\n",
    "    <input id=\"password\" type=\"password\"/>\n",
    "    <button onclick=\"done()\" style=\"border-radius: 12px;\">Submit</button>    \n",
    "</div>\n",
    "<button onclick=\"unlock()\" style=\"border-radius: 12px;\">Unclock</button>\n",
    "<a href=\"#\" onclick=\"code_toggle(this); return false;\">show code</a>\n",
    "\"\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%run loadmlfuncs.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# A First Look on Deep Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There is a set of 60,000 training images, plus 10,000 test images, assembled by the National Institute of Standards and\n",
    "Technology (NIST). Each image is a gray scale 28 $\\times$ 28 pixels handwritten digits. we're trying to classify images into their 10 categories (0 through 9)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "training images:(60000, 28, 28), test images:(10000, 28, 28)\n"
     ]
    }
   ],
   "source": [
    "from keras.datasets import mnist\n",
    "(train_images, train_labels), (test_images, test_labels) = mnist.load_data()\n",
    "print('training images:{}, test images:{}'.format(train_images.shape, test_images.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7d80719ab48548439f1b5fdadbb56d20",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(RadioButtons(description='Data:', options=('train', 'test'), value='train'), IntText(val…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def showimg(data, idx):\n",
    "    span = 5\n",
    "    if data=='train':\n",
    "        if idx+span<train_images.shape[0]:\n",
    "            images = train_images\n",
    "            labels = train_labels\n",
    "        else:\n",
    "            print('Index is out of range.')\n",
    "    if data=='test':\n",
    "        if idx+span<test_images.shape[0]:\n",
    "            images = test_images\n",
    "            labels = test_labels\n",
    "        else:\n",
    "            print('Index is out of range.')\n",
    "    plt.figure(figsize=(20,4))\n",
    "    for i in range(span):\n",
    "        plt.subplot(1, 5, i + 1)\n",
    "        digit = images[idx+i]            \n",
    "        plt.imshow(digit, cmap=plt.cm.binary)\n",
    "        plt.title('Index:{}, Label:{}'.format(idx+i, labels[idx+i]), fontsize = 15)\n",
    "    plt.show()\n",
    "\n",
    "interact(showimg,\n",
    "    data = widgets.RadioButtons(options=['train', 'test'],\n",
    "                                value='train', description='Data:', disabled=False),\n",
    "    idx = widgets.IntText(value=7, description='Index:', disabled=False));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Network Architecture\n",
    "\n",
    "The core building block of neural networks is the *layer*, a data-processing module working as a filter for data. Specifically, layers extract representations out of the data fed into them in a more useful form which is often called features.\n",
    "\n",
    "Most of deep learning consists of chaining together simple layers that will implement a form of progressive data distillation. A deep-learning model is like a sieve for data processing, made of a succession of increasingly refined data filters the layers.\n",
    "\n",
    "```python\n",
    "network = models.Sequential()\n",
    "network.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))\n",
    "network.add(layers.Dense(10, activation='softmax'))\n",
    "```\n",
    "\n",
    "Here, our network consists of a sequence of two densely connected (fully connected) layers. The second (and last) layer is a\n",
    "10-way softmax layer, which means it will return an array of 10 probability scores (summing to 1). Each score will be the probability that the current digit image belongs to one of our 10 digit classes."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compilation\n",
    "\n",
    "Before training the network, we need to perform a compilation step by setting up:\n",
    "\n",
    "- An optimizer: the mechanism to improve its performance on the training data\n",
    "\n",
    "- A loss function: the measurement of its performance on the training data\n",
    "\n",
    "- Metrics to monitor during training and testing\n",
    "\n",
    "```python\n",
    "network.compile(optimizer='rmsprop',\n",
    "                loss='categorical_crossentropy',\n",
    "                metrics=['accuracy'])\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Preparation\n",
    "\n",
    "```python\n",
    "train_images_reshape = train_images.reshape((60000, 28 * 28))\n",
    "train_images_reshape = train_images_reshape.astype('float32') / 255\n",
    "\n",
    "test_images_reshape = test_images.reshape((10000, 28 * 28))\n",
    "test_images_reshape = test_images_reshape.astype('float32') / 255\n",
    "\n",
    "train_labels_cat = to_categorical(train_labels)\n",
    "test_labels_cat = to_categorical(test_labels)\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fitting\n",
    "\n",
    "We train the neural network so that it can classify images in test image set.\n",
    "\n",
    "```python\n",
    "network.fit(train_images_reshape, train_labels_cat, epochs=5, batch_size=128)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From C:\\Users\\mzhao\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\tensorflow\\python\\framework\\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Colocations handled automatically by placer.\n",
      "WARNING:tensorflow:From C:\\Users\\mzhao\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\tensorflow\\python\\ops\\math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.cast instead.\n",
      "Epoch 1/5\n",
      "60000/60000 [==============================] - 4s 63us/step - loss: 0.2540 - acc: 0.9247\n",
      "Epoch 2/5\n",
      "60000/60000 [==============================] - 4s 63us/step - loss: 0.1055 - acc: 0.9691\n",
      "Epoch 3/5\n",
      "60000/60000 [==============================] - 4s 61us/step - loss: 0.0690 - acc: 0.9793\n",
      "Epoch 4/5\n",
      "60000/60000 [==============================] - 3s 56us/step - loss: 0.0510 - acc: 0.9847\n",
      "Epoch 5/5\n",
      "60000/60000 [==============================] - 3s 54us/step - loss: 0.0375 - acc: 0.9889\n",
      "10000/10000 [==============================] - 0s 47us/step\n",
      "test accuracy: 0.9778\n"
     ]
    }
   ],
   "source": [
    "from keras import models\n",
    "from keras import layers\n",
    "from keras.utils import to_categorical\n",
    "\n",
    "network = models.Sequential()\n",
    "network.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))\n",
    "network.add(layers.Dense(10, activation='softmax'))\n",
    "\n",
    "network.compile(optimizer='rmsprop',\n",
    "                loss='categorical_crossentropy',\n",
    "                metrics=['accuracy'])\n",
    "\n",
    "train_images_reshape = train_images.reshape((60000, 28 * 28))\n",
    "train_images_reshape = train_images_reshape.astype('float32') / 255\n",
    "\n",
    "test_images_reshape = test_images.reshape((10000, 28 * 28))\n",
    "test_images_reshape = test_images_reshape.astype('float32') / 255\n",
    "\n",
    "train_labels_cat = to_categorical(train_labels)\n",
    "test_labels_cat = to_categorical(test_labels)\n",
    "\n",
    "network.fit(train_images_reshape, train_labels_cat, epochs=5, batch_size=128)\n",
    "\n",
    "test_loss, test_acc = network.evaluate(test_images_reshape, test_labels_cat)\n",
    "print('test accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We reach an accuracy of 98.9% on the training data. However, the test-set accuracy turns out to be 97.8% — that's quite a bit lower than the training set accuracy as our errors are doubled. This gap between training accuracy and test accuracy is an example of **overfitting**."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction Error\n",
    "\n",
    "We demonstrate a few images that are misclassified by the trained neural network."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of misclassified images: 222\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x288 with 5 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "predicted = network.predict_classes(test_images_reshape)    \n",
    "result = abs(predicted - test_labels)\n",
    "misclassified = np.where(result>0)[0]\n",
    "print('# of misclassified images:',misclassified.shape[0])\n",
    "\n",
    "plt.figure(figsize=(20,4))\n",
    "for i in range(5):\n",
    "    plt.subplot(1, 5, i + 1)\n",
    "    idx = misclassified[i]\n",
    "    digit = test_images[idx]            \n",
    "    plt.imshow(digit, cmap=plt.cm.binary)\n",
    "    plt.title('Predicted:{}, Label:{}'.format(predicted[idx], test_labels[idx]), fontsize = 15)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "hide_input": false,
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": true
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {
     "00c2e2fcea4249a1ba250b2e40ed50c1": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "00c7d021fc0749a89f580d4f286830cb": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "0161623d644b45c9b25225bc1207ad86": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "01ea1d8b14344d1bae3f0ec7605d08ab": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_3682d0e06ace4d69bd0bf0963db10c9c",
       "step": 1,
       "style": "IPY_MODEL_8da9cbfbbc1f4cd880376f3340918c64",
       "value": 7
      }
     },
     "0315f967b7934712ac027e7c595b98dc": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "04b2c1c8d5814b3b96910f6318b694fc": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "079904e5f12948cd84187edcc132a0d4": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_ef6c009640b64f31a506936690e23692",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "08bf79865a2a4f9d8dd36f731de2eae3": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_5cc6b49b30b64f37af54128a8696e143",
       "style": "IPY_MODEL_0161623d644b45c9b25225bc1207ad86"
      }
     },
     "09d823911add4064b574339ac7e9e919": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "0c985c0a9a834020b472fba00d4263b9": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 1,
       "layout": "IPY_MODEL_d5f5464eec0e43eb84db9e867d06f9e3",
       "style": "IPY_MODEL_2bfcdcce67344a27a9167cc4616472d4"
      }
     },
     "0cb2219d39b34f9eba1c52a33d85830b": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_6404b8a2066547a7803fd35bd67b6694",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "0e267085d75a4770b279d8dc0d696650": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_345337fa9c9642668b7ac55017b616a5",
       "outputs": [
        {
         "ename": "AttributeError",
         "evalue": "'str' object has no attribute 'test'",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m<ipython-input-37-8c8290c93c3a>\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     10\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mspan\u001b[0m\u001b[1;33m<\u001b[0m\u001b[0mtest_images\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m             \u001b[0mimages\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtest_images\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m             \u001b[0mlabels\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     13\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m             \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Index is out of range.'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mAttributeError\u001b[0m: 'str' object has no attribute 'test'"
         ]
        }
       ]
      }
     },
     "0eb654de3f45498daded52839e210999": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_bb0d1743d1e94df2b9b1275823ae6da9",
        "IPY_MODEL_8d4ef1166513401aa5b1bc2e9a9e9644",
        "IPY_MODEL_81e092023f7943b5863949d9c1e3d6d2"
       ],
       "layout": "IPY_MODEL_ed34214dc73e4f29964958c078ca1b45"
      }
     },
     "0ee5ce8bc70747f48657e1d27692916f": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_8957a6314e084f20b1309e0dfdae959f",
       "style": "IPY_MODEL_19295357faaa432bbe38c2f576c8559b"
      }
     },
     "0f724e736e35441585282559a145abfd": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_da42c8e581b446c09491b33fe3d9700f",
       "step": 1,
       "style": "IPY_MODEL_3a69d4af166e4eacaa341262d31265b7",
       "value": 7
      }
     },
     "12597650ff034e3183cd86eaa9706e43": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "130ddb19822c483793ef93cf6784e1ec": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "14034ecacb884e2ba54d506875da6a86": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "1550c9b1e9d44b9b91f8edb789cefc21": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "16eb75aed3a94d73bb78f1013a6df7c4": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_63f0621888a147b78ff4551deea5b214",
       "style": "IPY_MODEL_4519c2e1ebec47c3b2e4f03ce5f3f786"
      }
     },
     "17dd22a77be04c86b54f068355a23b1f": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 1,
       "layout": "IPY_MODEL_dd6302e8933b4eaeba40db8c4a7a5768",
       "style": "IPY_MODEL_89c4ed731f3247e187dcd426f63ae484"
      }
     },
     "17ea7648990c4d758a5477ef85a6ccb0": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "1863cdb927484671a13bc2eb3e3888d8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_34b93d65b4f444bbbf35751f7c1b426b",
       "style": "IPY_MODEL_d0cf46cdf0d740fa83350c3093414e17"
      }
     },
     "1870402d6f0a44ffaa0cb2591f663b7b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "18e8908201d942c68622f497a6a06c55": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "19295357faaa432bbe38c2f576c8559b": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "1977a091ce4e45b89d59d5c037f3ea7b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "19a1a4c07cc14d34910e28c5706218b1": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_4197880989fd49e7b22f12a75d696665",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "1b9ac7a01d104dffa0fb6ac2caf86ae8": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_57f5b0ed80224d40ad0bb8a807ee20a5",
       "outputs": [
        {
         "data": {
          "image/png": "iVBORw0KGgoAAAANSUhEUgAABIEAAADxCAYAAABcW6cTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3XvcVXPe//H3R0JFQmVKRnOPUyY3EREzIqOccmaccxtqjJkhM8a45U7SOB9mhkjcOcyIMWUQY9zRMINIJfk5E1LIIRWmA5/fH2tdXO32d1372se1r/V6Ph77oWt99lrrcy3X+7r2/u611tfcXQAAAAAAAGjZ1qh1AwAAAAAAAKg8BoEAAAAAAAAygEEgAAAAAACADGAQCAAAAAAAIAMYBAIAAAAAAMgABoEAAAAAAAAyIFODQGY2wsw+LNO2epqZm1m/cmyvyB66mNn/mtm7ZrbUzGaa2bFFbsvN7PQS+ynn8R1vZtOLWG9w/L3kPoaWoy9URgvMZgczu9nMPo6z+aCZbV7ktlpENuN1Dzaz2Wa2zMzeNLNh5egJ5dECc3iamU02s4+SejGzbcxsipl9bmbzzWykmbUqYn9lOX7lyHy8ne7xtg4oYl0zs3PN7B0z+8LMHjOz7UvtCcXJYjbNbHMzu8HMnjOzL81sagn7azHZjNff1szuN7NPzWyJmT1tZjuW2heaL6PZPMLM7m30/vNZMzu6yP01vG9bt8S+55rZ5aVso9G2isq5ma1tZlea2Xvx64nHzax3OXqqhEwNArUkZraGpHsl7SHpbEkHSXpK0u1mdkgte0uJvSTt2ugxsbbtIGPulDRA0i8kHSNpI0lTzKx9TbuqITPbTVEOn5Z0oKSbJV1iZmfUtDG0ZCdI2lDSQ6EnmNkGkv5Pkiv6OzpS0lmSLqhGgyl2jqThki5RlNelkv7PzL5V067QUjSZTUnfk7SfpFfiByTFg7FPSFok6ShJR0i6T1KbWvaFFqOQbA5T9DfhTEmDJD0q6U9m9rPKt5dqv5N0sqQRkg7TN383N6tlUyFr1roBFG1LSb0lDXL3++JlU8ysj6QfSZpUs87S4Rl3X1rrJpA9ZrarpH0k9Xf3R+Jl0yS9KelUSWX5pKIOnS/pn+7+4/jrv8dvwM83s+vcfXkNe0PL1NfdvzKznpJCn1IOVfTm6VB3Xyzp4XiwdoSZXRovyxQzW0fRINBv3f0P8bInJc2VdLqk82rXHVqIQrJ5n7v/VZLM7G5JHavWXbpdr+jYHNdo2d9q1QxanEKyeaC7Nz776REz66pocOj3Fe8whcysm6IBoFPd/eZ42SOS3pD0K0V/O1Ml02cCmVm/hlPdzOzP8Sltb5jZaXmee1p8WvRnZnafpC55nrOGmZ1jZq9ZdLnDK2Z2YqP6d+LTNkc2WtbazGbEp1o35/9H6/i/n+YsXyTJmrGdgpjZ/mb2sJl9YGaLzewpM9sn8Nzd4u/p32Y2y8x2z/OcH5vZC/FxesvMzi53z6hfdZ7N7SWtlPSPhgXu/r6k2ZL2b8Z2ClJH2dxe0RkXjf1d0gaKztZDytR5DuXuXxXwtH0lPZQz2DNB0cDQHs3ZX1PMrJ2Z/cHMXrboVPE3zexay3+G4Fpmdo1Fl5QuMrPfm9laOdv7tplNiJ/zuZk9ZGZblaHVvpLaS7qrYYG7f6bobIN9y7B9lCgL2Swwv2VRL9k0s20k9VFG32jXg4xkM9/lbzMldW7OvgplZheb2fPxsZxnZn+0wFmpZjbcosuxlsbPWz+nvqFFl5m+b9Fr4ScsOoGiVNtKaqVGr3PdfZmkx1WB1/7lkOlBoEZulPScpEMkTZV0rZnt3FA0s4MkXSvpfkmHSnpe0aUMuX6v6BOysYr+h0+SdLPF1/y6+5uSfinpN/bNNYLnKTqr56SG4Fl0fak30fMcSdMkjTSzLcysvZkNlrSbok8Jyu07il4AHq/oFLcnJD1o0SUejbWVdHvcwxGKBqUebBxWM/uVpDGS7pF0QPzvC62J6y/jX6ojCuz3dTNbGf9BH1LgOkifeszmOpJWuvuXOcuXSepRwPfcXPWSzXUk5Z7tsyz+byWOC8qnHnNYqK0lvdR4gbu/LenzuFZObRW9SPxvRYMpwxVduvznPM89S1I3ScdKGqXoLMKLGopmtqGkf0raStHZTEdKaqfo1PPgZSEFHrutJX0p6dWc5S+q/McEpWnJ2aymeslmw5vVDSy6V9JKM3vdzE5u+ltElWUtm30l/b8KbbuzpNGKvv8zJP2HorOPcu/dd7SkvSWdouispP0ljWsomtnaigZpfqjo7JyDJS1UE5c62zf3Leqe0OM68X/zvc7dzMzaJqxbG+6emYeia/Q+bPR1P0X3ARjZaFlrRT8QFzda9rSkB3O2dWO8br/4680lfSXpxJzn3aro0qTGy/4m6QVFgVkh6Sc59fMVvYls6vvZQNJjcR+u6Afv2CKPjUs6vcDnrqHoUsKHJN2cc3xd0jGNlq0r6eOG46no08Wlkv4nZ5sjJb0nqVX89XhJ03Oes1LS+U30NkDRL799FP0hvzXu6cxa//zxSPz/1mKyqej+GS5p20bL2kj6SNLyIo5NS8nms5L+krPs13Ff59b6Z5BHy8phzvN7Nu4lp7ZC0hl5ls+TNLqU41fA89dU9MGNS/p2o+WuaGBqjUbL/lvRwNSG8dcXxr9TNmz0nA0UnR380/jr7vG2DmjOsYv3tSjP8h/H21ur1j+rWXtkMZs5z7tb0tRyHb8Cnp/WbP4mXu9DRfcD3VPRQIJL2q/WP6dZfGQ9m/Fz+8d9Di7i+A2O97Nugc9vJWmTeJ0fNFo+V9Fr2nUbLTs27qtH/PXJit4rb9HoOWtKel3SZY2WrfK6W9F9klZK2iyhr23j9Q5stMwUDYy5pK61/lnNfXAmUOTvDf9w9xWKPv3qJknxKGMvSX/NWSf3RsMNAZhkZms2PCRNkbR9zmjlyZK6SnpE0qPuPqbxhtx9pLsn3q8pPr3vNkU3nD1K0R+CqyXdZGYDm/6Wm8fMupnZLWb2rqIgrFA00LJlnqd/fT8ij+7L87CkhtHvXRV9IvLnnOP0iKSNFR/3fNx9TXcfGarHz3nI3Ue5+9/d/UF3P0HRKe3nNfeUSKRC3WVT0QDMm5JuMLOtzKyLorNv1lf06XpZ1Us2FR2Dg8zsFDPbwMwGKPpEVarAcUFZ1WMOm8PzLLPA8pKY2fEWzeS5VFFW/xmXcvP6V1/1tPyJigaTe8Zf760ov4sbHcsligZbg7ORNOPYhY5JqIbaaOnZrJo6yWbD69hx7n6puz/q7j9VdGPe3zSxLqorE9mMz475k6JcjC/39uN97BtftvWpote58+JSbjYf9lXvBztR0d+tneKv91aUwzcbHUspun1DUjZvjV/nvpXwnOcl/UvS5Wa2o5l1UnT2UkOPqXudy5viyKKcr5frm9O6OikaJfwg5zm5X3dUNDr5qaI/Hg2P8fH6X1/n6e7vKrpGcG1Fl1sU4wBFp7kd7O53uftUdz9b0Zu8S4vcZl72zUxkfRWNJO+pKFAP6pvj1GCpu3+Rs+wDffP9N9zY7wWtepwejZdvWs7eY3crutN99wpsG5VVd9n06AbHP1I0cPKSpPmKTl29VdL7xWwzpM6yebOigaAxij6tmajoLCOpzMcFZVd3OWyGTyR1yLN8fa3+fZfEopk7b5X0pKJLMndRdKmAtHpeQ8ezcV6P0qrHcoWi3wGlZvUTSevlOdW+g6TP4zc0SIeWnM2qqaNsfhz/99Gc5Y9I2qbEbaO8Wnw240sfH5T0tqTjmnh6sfvYSdHr3HmKbnuwq6J8Sk1kM37Nu1SrZnMXrZ7Nk1Se95+DFZ0VOD3u5UBJ18T7+Di8Wm3U5Wh9lS1UNOqYe7Or3K8/jp+3m6JR21xf/2DGf2wOUHSt6KVm9pC7f97MvrZW9GIs95r9mYqm6yunzRWNWO/r7l/PQBC4tnldM2uT82azs6QF8b8bQnCA8r/xe7kM/Ybw6WXLktZsyt2fNrPNFX0CsNLdXzez+yU91dxtNaFusunRPZJON7Phij4Ne1Pf3F+k3McF1ZPaHBboJeXc58bMNlV0VtxLedco3hGSprn71zcINbM9As8NHc/Geb1X0aUnuZaU0qSi77uVot8vjXO/2v2TkGr1ns1qqpdsvhhYbsr//w7pVPfZjO9xc7+ktSTt79HkAZVwiKLjdZQ3XGMVnnJ9leMXvxZeV6tmc7qkn+RZd1meZc3i7q9J6mVm/6HoEsBXFN3TaUYaPzzhTKAmxG9cZkk6KKd0aM7Xjyh60bS+u0/P81guSWbWUdGn4ddJGqjoDJVLimjtLUltbfXZBnZUdF1kOTW8ofw6IHEAc2882+CQRs9bV9ENuJ6OFz0p6QtF10bmO06l/oHM5zBF108HT+ND/UlxNhv6c3d/OR4A2kLRaag3Fbu9gLrLprt/4u7Px6fsnibpCXfnjWWdSnsOC/CgpAFmtl6jZUcpysI/8q9StDZa/YXmsYHnHpRzCfOhcU9z4q+nSPqepBfyHMtSP0x5QtJiRW+MJX39gv9ARccLdaAFZLOa6imbnyi6TKix/ore/KMO1Hs248uo/ixpC0UfQuaewVRObSStaBgAioWy+cP4tW2DQxWdADA9/nqKog833s5zLJ8vV8Pu/kac9Y0U3Ri+3K/9y4IzgQozWtJEMxuj6HKrPRSF7Gvu/rKZXS9pgpldqugHbh1Ffwi2dPcfx08do+iTgF+7+2dm9lNJfzKzie7+qCSZ2fmKbrKa9P/nAUWn391j0bSACxVdHnakpJ82PMnM+ik6bXRPd5/axPe5vZkdnrNsoaJP6edJuiL+FH89SRdIejfPNr6QdFEcwvmK7li/lqLT4eTuiyyaReia+M3qY4oGI7eMezwkzzYbvpeVim60Frz3iJn9RdGb2tmKfnEeFT9+7lWcbhRVk8ZsKs7JS4oGH7dVNNPIBHd/uNFz+ilb2dxF0u6KXvi0VzSLw4B4GepbWnPYW9FlwA2nee8Rv1ie6+4NLwqvl/TzuP9LFF26OULSld5o2ngzmxp/H/2aOBZr5cmqFA0oPaxohpj/VjS7535a/c1cg/UU3Z/rRkXH6HxJf3D3hjP2rlR0+v0jZvZ7RZnfWNGx/6e735Fvo4UcO3f/t5ldLGm4mX2i6HfZMEW/D5iaur7UbTbjgcf94vomkto3ytYDDWc5ZCyby+PX/Jea2SJJzyj6oPMH8fZRP+o2m4oGm/aT9AtJG8av7xrM9GhqdJnZeEU3lu5ewPE42Mz+nbPsGUXZPMPMrlY0E25fhS89+0LSZDO7TNElYJdJmuTuDbOW3apoxr6pZna5pDcUDdTsLOk9d78q30bN7ARFtzT4rifcF8jMfq7opvDvKhog+42iWd9SOQhU8ztTV/Oh8B3ce+Y8b6qku3OWna7ozdbnigZg9lHOXdMVnY55hqJ7aixT9CbtH5JOiOtHK7ox1O45275L0dk76zXq0wv4fjZXNBI7X9E1j89JGiLJGj1nv7jPbZrYlgceU+P6TooGV75QdHOzwcqZJajh+Er6vqI3esvinn6QZ3/HKbo51xeKPtWYJmlYo/oq227U44gmvo/Rik5f/zze9rOSjq/1zx6PJn+WW1o2r1b0R2CZpNcUzYK1Zs5zspbNHRX9QV+q6CyDyWo0gxqP2j9aYA7HB7IzPud52yj6xPULRaeNX6h4NrxGz3la0l0FHL9QXvsp+mDickWn8C+W9BdFUz67Vp0lyBUNuvwhzuCnimYAWjtnf10l/a+iyzeXxcfodknfi+vd82y70GNnimY9mhcfl8cl9ar1z2hWH1nMZqOf33yP7o2el6lsxs8dpuiS6uWK3mQeWuuf0aw+MprNuQVm8y5JTzexv8EJ2xocP+dsSe9I+kzRFO9bxPXTc3q6Iv4+34+fe4ekDjn7W1/Rh5/vxPmZp+gelbs1ek7utht67N7E9/LrOJfL4u1fIqltrX9GQw+Lm0YLZWYXKHqjt2etewHwDbIJ1AczW1vRG8N93L3cl4gBKBLZBNLLzN5SdPbRLbXuBavjnkAtX19Fp6YCSBeyCdSH3pLm8CYTSB2yCaSQmXVVdHPkvJc/ovY4EwgAAAAAACADOBMIAAAAAAAgAxgEAgAAAAAAyICqThHfsWNH7969ezV3CaTG3Llz9eGHH1qt+8iHbCLLyCaQTmQTSCeyCaRTodksaRDIzAYqmmatlaRx7n5x0vO7d++u6dOnl7JLoG717t27avsim0DhyCaQTmQTSCeyCaRTodks+nIwM2sl6VpJ+0raRtLRZrZNsdsDUB5kE0gnsgmkE9kE0olsApVRyj2Bdpb0mru/4e7LJU2QdFB52gJQArIJpBPZBNKJbALpRDaBCihlEGgTSe80+npevGwVZnaqmU03s+kLFy4sYXcACkQ2gXQim0A6kU0gncgmUAGlDALlu+GQr7bAfay793b33p06dSphdwAKRDaBdCKbQDqRTSCdyCZQAaUMAs2TtGmjr7tJml9aOwDKgGwC6UQ2gXQim0A6kU2gAkoZBHpG0hZm9h0zW0vSjyTdW562AJSAbALpRDaBdCKbQDqRTaACip4i3t1Xmtnpkh5SNGXfze7+Qtk6A1AUsgmkE9kE0olsAulENoHKKHoQSJLc/QFJD5SpFwBlQjaBdCKbQDqRTSCdyCZQfqVcDgYAAAAAAIA6wSAQAAAAAABABjAIBAAAAAAAkAEMAgEAAAAAAGQAg0AAAAAAAAAZwCAQAAAAAABABjAIBAAAAAAAkAEMAgEAAAAAAGQAg0AAAAAAAAAZwCAQAAAAAABABjAIBAAAAAAAkAFr1roBAAAAAPVt2bJlwVrfvn2DtZkzZwZrgwYNyrv8nnvuKbwxAMAqOBMIAAAAAAAgAxgEAgAAAAAAyAAGgQAAAAAAADKAQSAAAAAAAIAMYBAIAAAAAAAgAxgEAgAAAAAAyACmiEdJPvnkk2Dt7bffLvv+Nttss2DtqquuCtZ69uyZd/mWW24ZXGe77bYrvDEAQM09/vjjwVrSFNUvv/xy3uX3339/cJ3JkycHa/vvv3+wlmTXXXcN1r7//e8XtU2gnJKmgT/zzDODtVmzZgVrZhas7bjjjoU1BgAoGGcCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACzg0FS8gwo9913X7A2derUYO3VV18tpaW8ttpqq2Bt7ty5wVrSbBYhX331VbPXAQCUbvHixcHascceG6xNmTIlWGvTpk2wtmLFirzLlyxZElwnyWOPPVbUekk9tmvXLlgbM2ZMsHb44YcX1QuQz+9+97tg7YYbbgjW+vfvH6yNHDkyWNtll10KawwAULCSBoHMbK6kJZK+lLTS3XuXoykApSGbQDqRTSCdyCaQTmQTKL9ynAm0p7t/WIbtACgvsgmkE9kE0olsAulENoEy4p5AAAAAAAAAGVDqIJBL+ruZPWtmp+Z7gpmdambTzWz6woULS9wdgAKRTSCdyCaQTmQTSCeyCZRZqYNAu7n7DpL2lfRTM/tB7hPcfay793b33p06dSpxdwAKRDaBdCKbQDqRTSCdyCZQZiUNArn7/Pi/H0iaJGnncjQFoDRkE0gnsgmkE9kE0olsAuVX9I2hzaydpDXcfUn8730khed4RFm9/vrrwdq1116bd/nYsWOD63zxxRfBmrsX3liFvfzyy7VuIfXIJpBOZLNwv/71r4O1+++/v6htJv2d69GjR97lnTt3Dq7Tvn37ovr46quvgrXJkycHa0n9n3zyycHalltuGaz953/+Z7CWJWSzcAsWLChqvb333jtYYxp4hJBNoDJKmR1sY0mTzKxhO39y97+VpSsApSCbQDqRTSCdyCaQTmQTqICiB4Hc/Q1J25WxFwBlQDaBdCKbQDqRTSCdyCZQGUwRDwAAAAAAkAEMAgEAAAAAAGQAg0AAAAAAAAAZwCAQAAAAAABABpQyOxhqaN68ecHa1VdfXcVOym/rrbcO1nr27FnFToDyeu211/Iu//DDD4PrTJo0KVibOnVqsLbGGuEx/qFDhwZrffv2Dda22GKLYA1orjlz5gRrd999d1Hb3HTTTYO1W2+9NVjbfPPN8y7v0KFDcJ1111238MYaSZoifuTI8MzHF154YbC2ePHiYG3EiBHB2k033RSsbbDBBsEasmvp0qXB2lprrRWsJU0RDyCdZs6cGawNHz487/IHHngguI67B2vxDHB5HXHEEcHaRRddFKx16dIlWHv00UeDtf79+wdrbdq0CdbqCWcCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAFPFlkjTFc9KU7bvvvnuwNnDgwGAtaRrO9ddfP+/ypOlsk6b8HDBgQLCWNGV7nz59grVevXoFa0lT77Vr1y5YA6rl+eefD9auvfbaYG3ixIl5ly9cuLDknprjqaeeCtZat24drG211VbBWtLvsmuuuSZYS/pdhpYt6e9O0t/UpGlkzz777GCtX79+BfVVaWusEf78LWk69+XLlwdrl19+ebA2adKkYO2//uu/grUDDjggWEPLNn/+/GBt3LhxwVrfvn2DtR122KGkngAUb8WKFcHaP/7xj2Bt8ODBwdqCBQvyLk/6G50kab277747WEt63/j2228Ha1OnTg3Wbr311mDtuOOOC9bqCWcCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAFPHN8NlnnwVrP/zhD4O15557Lli75557iupl1113DdZmzpyZd3n37t2D6yRNodetW7dgLWmqWyDtZs+eHawlTfV+5513Bmuffvpps/tIytj3v//9YC0p05dddlmwtuOOOwZr06ZNC9Y++uijYO2BBx4I1rbbbrtgbejQocEaWrZly5YVtV7SlLWnn356kd2k3+jRo4O1CRMmBGtvvvlmsDZx4sRgjSnis2vUqFG1biF1nnzyyWBt3rx5RW0z6W/jlltuWdQ2gXxmzJgRrA0YMKCobXbt2jXv8j/84Q/Bddq2bVvUvt56662itvmzn/0sWFt77bWDtS5duhTWWB3jHTwAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAU1OEW9mN0s6QNIH7t4zXrahpDsldZc0V9KR7v5J5dqsnuXLlwdrxxxzTLCWNA38ueeeG6ztvffehTXWDEnTRod8+9vfLnsfqKysZbNYQ4YMCdYmTZoUrC1cuLCo/SVletttt827PGnq53XWWaeoPpKmsx0zZkywdtJJJwVrs2bNCta+9a1vBWunnXZasHbYYYflXd6pU6fgOmlHNgszfPjwotbr06dPmTupfwMHDgzWkvL+1FNPVaKd1CKbhZk8eXJR6/34xz8ucyfl95Of/CRYS/q+P/kk/CPx+eefF9VL+/btg7Vhw4YFa8X+7kwzslm6OXPmBGuDBg0qaptJr2l/+9vf5l2+ww47FLWvJPPnzw/WDjrooGBt0aJFwdrZZ58drPXv37+wxupYIWcCjZeU++riHElT3H0LSVPirwFU13iRTSCNxotsAmk0XmQTSKPxIptA1TQ5COTuj0n6OGfxQZJuif99i6SDy9wXgCaQTSCdyCaQTmQTSCeyCVRXsfcE2tjdF0hS/N/O5WsJQAnIJpBOZBNIJ7IJpBPZBCqk4jeGNrNTzWy6mU0v9h4bAMqPbALpRDaBdCKbQDqRTaB5ih0Eet/MukhS/N8PQk9097Hu3tvde9fzjT6BOkE2gXQim0A6kU0gncgmUCHFDgLdK+nE+N8nSvpredoBUCKyCaQT2QTSiWwC6UQ2gQopZIr4OyT1k9TRzOZJ+h9JF0u6y8xOlvS2pCMq2WS5LV26NFhLmqr5vvvuC9aSRp1/9atfBWtt27YN1oAkLTGbSf79738Ha5deemmwduONNwZr7h6sde4cvvQ8aYrZpLy3a9cuWCu3jz76KFhbuXJlsHbBBRcEawMGDAjW5s6dW1BfWZC1bCZ54403grV33303WOvQoUOwtu2225bUU0u01157BWtJU8RnDdn8RtK05itWrAjWunXrFqwNHjy4lJbyCv29mjFjRnCdgw8O3z/4vffeC9aSXhMkvc5PmkY7qc+33347WLvhhhuCtRNOOCHv8s022yy4TtqRzdKNGjUqWEu6RO6AAw4I1q644opgbYsttiissTKYM2dOsJaUsSQDB+ZORpctTQ4CufvRgVL/MvcCoBnIJpBOZBNIJ7IJpBPZBKqr4jeGBgAAAAAAQO0xCAQAAAAAAJABDAIBAAAAAABkAINAAAAAAAAAGcAgEAAAAAAAQAY0OTtYS3TPPfcEaxdffHGwljT14uOPPx6srb/++oU1BiBo6tSpwdpll10WrCVN+brJJpsEaxMnTgzWdt5552Ct3L788stg7Z133gnWQlPIStL+++8frH3yySeFNdYMxx9/fLCWNBU46t/tt98erCVNH3/44YcHa3379i2pJwDSuHHjgrX3338/WBsyZEjZe5k/f36wNnbs2LzLL7zwwqL2lfR3P+lv1WmnnRasdevWraheBg0aFKxNnjw5WFuwYEHe5fU8RTwKc8oppwRrd911V7C27rrrBmtJ732rOQ38ihUrgrXf/va3wVrS6/x+/foFa3vssUdBfbVUnAkEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZEAmp4h/4oknilqvV69ewVqx00MCKMzKlSuDtVatWhW1zdatWwdr06ZNC9buvvvuYO2ll15qdh9t2rQJ1l588cWiah07dgzW3nvvvcIaa4aNN944WDvvvPOCtaT/B6h/d9xxR7DWoUOHYO0Xv/hFJdoBEJs5c2ZR61ViyuhRo0YFa9dff33e5WYWXKd///7B2pVXXhms9ezZM1irhM0337yq+0P9mz59erCWlIl27doFa9tss01JPTVH0jTww4cPD9Yee+wCr8ieAAAUvklEQVSxYC3p+z7//PMLayyDOBMIAAAAAAAgAxgEAgAAAAAAyAAGgQAAAAAAADKAQSAAAAAAAIAMYBAIAAAAAAAgAzI5O1jSzD5JHnzwwWDtggsuCNYGDRoUrCXNOAbgG0mzfey5557B2sMPPxysvfXWW8Haz3/+88Iaa4Y118z/Kzdp5rNiFTsD2BprhD8bOPTQQ4O13/3ud8Faly5diuoFLdvWW28drO2+++5V7ATInvnz51d1f6+88kqwNmHChGZv79RTTw3WrrnmmmBtrbXWava+amHHHXcM1nbYYYcqdgI0z9y5c4O16667Lli74ooritpf165dg7Xtt9++qG1mAWcCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABmQySniFy5cGKyZWbC2bNmyYC1pivhRo0YFa0OHDg3W+vTpE6y98847wdrmm2+ed/n3vve94DpJXnjhhWBt1113Dda6detW1P6AfNq0aROsTZo0KVhbtGhRsHbxxRcHa//617+CtY022ihY+/a3vx2shX6HPPfcc8F1pk2bFqxVwpAhQ4K10aNHB2sdOnSoRDuoA5999lmwtnLlyip2AqBQixcvDtbcvahakt///vfBWtLf6WOPPTbv8jFjxhTVR5osXbo0WFtzzfBbtHqZ5h7l16NHj2Bt9uzZwdrHH38crPXq1auknnIlvc+eP39+sJb0HjxJ//79gzVem4Y1eSaQmd1sZh+Y2ZxGy0aY2btmNit+7FfZNgHkIptAOpFNIJ3IJpBOZBOorkIuBxsvaWCe5Ve5+/bx44HytgWgAONFNoE0Gi+yCaTReJFNII3Gi2wCVdPkIJC7PyYpfA4ZgJogm0A6kU0gncgmkE5kE6iuUm4MfbqZzY5P39sg9CQzO9XMppvZ9KRrBAGUDdkE0olsAulENoF0IptABRQ7CDRG0nclbS9pgaQrQk9097Hu3tvde3fq1KnI3QEoENkE0olsAulENoF0IptAhRQ1COTu77v7l+7+laQbJe1c3rYAFINsAulENoF0IptAOpFNoHKKmiLezLq4+4L4y0MkzUl6ftr88pe/DNauuCI4yFy0L7/8Mli79tpri6qlRefOnYO1fv36BWsTJkyoQDeo92xWQtL0kElTxFfTCSecEKwVO0V8+/btg7Urr7wyWBs8eHCw1qpVq6J6QcvO5p133hmsvfbaa8Fax44dK9FOJt17771Frde6desyd1J/WnI2kyRNx1xsLUmxU0MnrVcPkvofN25csHbYYYdVop26ktVsJrnpppuCtSVLlgRrkydPDtaSppYvt6S/VbfddluwdvfddwdrQ4cOLamnrGpyEMjM7pDUT1JHM5sn6X8k9TOz7SW5pLmShlSwRwB5kE0gncgmkE5kE0gnsglUV5ODQO5+dJ7F4WFIAFVBNoF0IptAOpFNIJ3IJlBdpcwOBgAAAAAAgDrBIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZEBRU8TXu6RpoY888shg7dhjjw3WVqxYEazNmzcvWEuaPr4efPDBB8Han//852CtZ8+ewdp5551XUk9AWl166aV5l0+YMKHs+xozZkywdswxx5R9fwAq69lnnw3W7rvvvqK2edFFFxXbDtAsY8eODdaeeOKJZtdGjx4dXGfIkPAkUhtttFGwVgmHHnposNa2bdtg7ayzzqpEO6hzbdq0CdaS/g5MnTo1WJs+fXpRvWyzzTZ5l++3337BdU477bRgLel941ZbbRWsffe73w3WEMaZQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGZHKK+FatWgVrO+20U7D2yiuvFLW/KVOmBGtJU8uPGDEiWHv66aeL6qWa3D1YS5rqFqhn48aNC9ZGjRqVd3nS74EkPXv2DNYOO+yworYJoHaS/jZeccUVwdqiRYuCtd133z1YGzhwYGGNoS7Nnz8/WFuwYEEVO0memn3GjBnB2qBBg/IuHz58eHCdhx56KFi7//77g7X11luvqPVCf9slaebMmcHaeeedF6ztsssuwRrQXP369SuqVm7XX399sGZmwVrS+/NOnTqV1FNWcSYQAAAAAABABjAIBAAAAAAAkAEMAgEAAAAAAGQAg0AAAAAAAAAZwCAQAAAAAABABjAIBAAAAAAAkAGZnCK+2vr371/UerNmzQrWkqaIb926dd7lJ510UnCdU045JVi76qqrgrU//elPwRrQUiXl76yzzgrWlixZ0ux9JU1ZO2bMmGBt7bXXbva+gGJ07949WGvfvn31GqkTX375ZbB2+eWXB2sTJkwI1rp161bUNtdck5eBLVnXrl2DtS233DJYe+utt4K1Rx55JFgbMmRIsNa2bdtgrUuXLsHaM888k3d50pTtPXr0CNYWLVoUrCX9/R43blywlvS9JU0DnzTNPVCv5s6dW9R6Sa93zzjjjCK7QQhnAgEAAAAAAGQAg0AAAAAAAAAZwCAQAAAAAABABjAIBAAAAAAAkAEMAgEAAAAAAGQAg0AAAAAAAAAZ0OTcoGa2qaRbJX1L0leSxrr7NWa2oaQ7JXWXNFfSke7+SeVazZ599tknWDv33HODtRUrVuRdPnbs2OA6r776arA2derUYK1Ym2yySdm3mTVks3buu+++YG3x4sXN3l67du2CtXvvvTdY23333Zu9L1Re1rK51157BWtJU1R/+umnwdqHH34YrHXs2LGwxips9uzZwdp1110XrM2YMSNYC02H3ZTbb789WOvTp09R22yJspbNJDfddFOwtv/++wdrkydPDtaSXrcOGzYsWEuaIj5k2rRpwdro0aOLWs/dg7WtttqqqP0dcsghwRq+QTZbjpEjRxa13gEHHBCs7bDDDsW2g4BCzgRaKeksd+8haRdJPzWzbSSdI2mKu28haUr8NYDqIZtAOpFNIJ3IJpBOZBOooiYHgdx9gbvPiP+9RNKLkjaRdJCkW+Kn3SLp4Eo1CWB1ZBNIJ7IJpBPZBNKJbALV1ax7AplZd0m9JE2TtLG7L5Ci4ErqHFjnVDObbmbTFy5cWFq3APIim0A6kU0gncgmkE5kE6i8ggeBzGxdSX+RdIa7F3zTC3cf6+693b13p06diukRQAKyCaQT2QTSiWwC6UQ2geooaBDIzForCuQf3X1ivPh9M+sS17tI+qAyLQIIIZtAOpFNIJ3IJpBOZBOoniYHgczMJN0k6UV3v7JR6V5JJ8b/PlHSX8vfHoAQsgmkE9kE0olsAulENoHqanKKeEm7STpe0vNmNitedq6kiyXdZWYnS3pb0hGVaTG7evToEawdddRRwdqdd97Z7H09+uijzV5HktZcM/wjlDTF6CWXXFLU/rAKsllBS5YsCdYuvfTSsu7ruOOOC9b69etX1n2hKshmAV588cVgbcCAAcFaMdNJV0LSVNNJU9wnSbqM4cADDwzWdtppp6L2l0FkM9atW7dg7W9/+1uwtueeewZrTz75ZLB2xBHFHdLQtO3RmEF5nXTSScFa0t/9jTbaqOy9ZBDZrDNz5szJu3zixIl5lzdl4MCBpbSDZmpyEMjd/ykp9Ju2f3nbAVAosgmkE9kE0olsAulENoHqatbsYAAAAAAAAKhPDAIBAAAAAABkAINAAAAAAAAAGcAgEAAAAAAAQAYwCAQAAAAAAJABhUwRjxpp06ZNsHb11VcHa6GprZ999tngOu+//36w1r1792DthBNOCNZGjBgRrAFpsHTp0mCtR48ewdry5cuL2t92222Xd3lSnoF6Nnr06GDtwgsvDNZmzJhRiXaqZo01wp+xJU0nPWzYsGDtnHPOKaknoFBdunQJ1p566qlg7c477wzWXnvttWDtxhtvDNZOPvnkvMuTMpYktD1J2nrrrYvaJpBFM2fOzLt88eLFwXXMQhPASeuss07JPaFwnAkEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZABTxNepjTfeOFi7//778y6/7bbbgus8+eSTwVrSVO+dO3cO1oC0e+SRR4K1d999t+z7u/LKK/MuZ1pMtFSHHHJIsNanT59gbeDAgcHa888/X1JP5XLqqacGa7169QrWhg4dWol2gKro0KFDsDZkyJCitnnZZZcV2w6AGlm4cGHe5UnTwPfs2TNYO/zww0vuCYXjTCAAAAAAAIAMYBAIAAAAAAAgAxgEAgAAAAAAyAAGgQAAAAAAADKAQSAAAAAAAIAMYHawDDn++OOLqgEt1fDhw8u+zbPPPjtY22uvvcq+P6Bede3aNVibPXt2FTsBAADNkTTrdAjvN9ODM4EAAAAAAAAygEEgAAAAAACADGAQCAAAAAAAIAMYBAIAAAAAAMgABoEAAAAAAAAygEEgAAAAAACADGhyingz21TSrZK+JekrSWPd/RozGyHpFEkL46ee6+4PVKpRAKsim6X7+OOPi1qvc+fOwdoZZ5xRbDtoIcgmkE5kE0gnsll/evTokXf57Nmzq9wJitHkIJCklZLOcvcZZraepGfN7OG4dpW7X1659gAkIJtAOpFNIJ3IJpBOZBOooiYHgdx9gaQF8b+XmNmLkjapdGMAkpFNIJ3IJpBOZBNIJ7IJVFez7glkZt0l9ZI0LV50upnNNrObzWyDMvcGoEBkE0gnsgmkE9kE0olsApVX8CCQma0r6S+SznD3xZLGSPqupO0VjdxeEVjvVDObbmbTFy5cmO8pAEpANoF0IptAOpFNIJ3IJlAdBQ0CmVlrRYH8o7tPlCR3f9/dv3T3ryTdKGnnfOu6+1h37+3uvTt16lSuvgGIbAJpRTaBdCKbQDqRTaB6mhwEMjOTdJOkF939ykbLuzR62iGS5pS/PQAhZBNIJ7IJpBPZBNKJbALVVcjsYLtJOl7S82Y2K152rqSjzWx7SS5prqQhFekQQAjZLNGwYcOKqg0fPjxY69KlS7CGzCCbQDqRTSCdyGad2XffffMuf+ONN4Lr7LTTTpVqB81UyOxg/5RkeUoPlL8dAIUim0A6kU0gncgmkE5kE6iuZs0OBgAAAAAAgPrEIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABlQyBTxANAinXnmmUXVAAAAgKw6/vjjm7Uc6cKZQAAAAAAAABnAIBAAAAAAAEAGMAgEAAAAAACQAQwCAQAAAAAAZACDQAAAAAAAABnAIBAAAAAAAEAGmLtXb2dmCyW9FX/ZUdKHVdt5srT0Qh+rS0sv5ehjM3fvVI5myo1sNok+VpeWXshmbaSlF/pYXVp6IZvVl5Y+pPT0kpY+pPT0QjarLy19SOnphT5WV7VsVnUQaJUdm01399412XmOtPRCH6tLSy9p6aMa0vS9pqUX+lhdWnpJSx/VkKbvNS290Mfq0tJLWvqohrR8r2npQ0pPL2npQ0pPL2npoxrS8r2mpQ8pPb3Qx+qq2QuXgwEAAAAAAGQAg0AAAAAAAAAZUMtBoLE13HeutPRCH6tLSy9p6aMa0vS9pqUX+lhdWnpJSx/VkKbvNS290Mfq0tJLWvqohrR8r2npQ0pPL2npQ0pPL2npoxrS8r2mpQ8pPb3Qx+qq1kvN7gkEAAAAAACA6uFyMAAAAAAAgAxgEAgAAAAAACADajIIZGYDzexlM3vNzM6pRQ9xH3PN7Hkzm2Vm06u875vN7AMzm9No2YZm9rCZvRr/d4Ma9THCzN6Nj8ssM9uvCn1samaPmtmLZvaCmf0iXl6LYxLqperHpdrIJtnM00cqspnlXEpkM9432Vy1D7KZAmSTbObpg2zWWFpyGfdCNslmoX1U7ZhU/Z5AZtZK0iuSfihpnqRnJB3t7v+vqo1EvcyV1NvdP6zBvn8gaamkW929Z7zsUkkfu/vF8S+sDdz91zXoY4Skpe5+eSX3ndNHF0ld3H2Gma0n6VlJB0sarOofk1AvR6rKx6WayObX+yabq/aRimxmNZcS2Wy0b7K5ah9ks8bI5tf7Jpur9kE2ayhNuYz7mSuySTYL66Nq2azFmUA7S3rN3d9w9+WSJkg6qAZ91JS7Pybp45zFB0m6Jf73LYp+GGrRR9W5+wJ3nxH/e4mkFyVtotock1AvLR3ZFNnM00cqspnhXEpkUxLZzNMH2aw9simymacPsllb5DJGNlfrg2zGajEItImkdxp9PU+1+4Xkkv5uZs+a2ak16qGxjd19gRT9cEjqXMNeTjez2fHpexU/TbAxM+suqZekaarxMcnpRarhcakCshlGNpWebGYslxLZTEI2RTZriGyGkU2RzRpJUy4lspmEbNYom7UYBLI8y2o1T/1u7r6DpH0l/TQ+VQ3SGEnflbS9pAWSrqjWjs1sXUl/kXSGuy+u1n4L7KVmx6VKyGb6ZT6bGcylRDbrAdkkmw3IZrqQzexlM025lMhmCNmsYTZrMQg0T9Kmjb7uJml+DfqQu8+P//uBpEmKTh+spffjawQbrhX8oBZNuPv77v6lu38l6UZV6biYWWtFQfiju0+MF9fkmOTrpVbHpYrIZhjZTEE2M5pLiWwmIZtks5bIZhjZJJu1kppcSmQzhGzWNpu1GAR6RtIWZvYdM1tL0o8k3VvtJsysXXwjJplZO0n7SJqTvFbF3SvpxPjfJ0r6ay2aaAhB7BBV4biYmUm6SdKL7n5lo1LVj0mol1oclyojm2Fks8bZzHAuJbKZhGySzVoim2Fkk2zWSipyKZHNJGSzxtl096o/JO2n6K7tr0v67xr18B+SnosfL1S7D0l3KDrNa4WiEeuTJW0kaYqkV+P/blijPm6T9Lyk2YpC0aUKfeyu6FTN2ZJmxY/9anRMQr1U/bhU+0E2yWaePlKRzSznMv7+ySbZzO2DbKbgQTbJZp4+yGaNH2nIZdwH2Qz3QTZrmM2qTxEPAAAAAACA6qvF5WAAAAAAAACoMgaBAAAAAAAAMoBBIAAAAAAAgAxgEAgAAAAAACADGAQCAAAAAADIAAaBAAAAAAAAMoBBIAAAAAAAgAz4/4DsnbPDyhKEAAAAAElFTkSuQmCC\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "1c1535a7cad445a2a41ec14b57b1048c": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "1d681d7c19db4b038faa3b90d3155fdf": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "1f6325aee9ad4d81bbf5cdb586b352f2": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_1870402d6f0a44ffaa0cb2591f663b7b",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "1fe1ff51f21c4c668e1a1e59338d5235": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_cad7e4bcc3804790ad5722afaa19a2f2",
       "step": 1,
       "style": "IPY_MODEL_5089eacaf98447e28aca6a2e79244a1e",
       "value": 7
      }
     },
     "20aef094b75243ffab1a2bea3b2b5ea4": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "21a382c120884dc4a4a6a81f7d80a244": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_affa269ad75b474799eda2bc0c4048dd",
       "outputs": [
        {
         "ename": "NameError",
         "evalue": "name 'np' is not defined",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m<ipython-input-35-8c8290c93c3a>\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     10\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mspan\u001b[0m\u001b[1;33m<\u001b[0m\u001b[0mtest_images\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     11\u001b[0m             \u001b[0mimages\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtest_images\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 12\u001b[1;33m             \u001b[0mlabels\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     13\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m             \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Index is out of range.'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mNameError\u001b[0m: name 'np' is not defined"
         ]
        }
       ]
      }
     },
     "22b375bb048e434dadcbdd4aecd7895a": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_be2b75873f6848269487653ccbae4dfa",
       "step": 1,
       "style": "IPY_MODEL_de24cf0b57bc409f9467a51b4b878663",
       "value": 7
      }
     },
     "2881ff2455614d48b61745237157e7ae": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "2b115a7c92e24b03bd788de53cd0deaa": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_4848c0fefd504447a7877758fbc2415a",
       "step": 1,
       "style": "IPY_MODEL_4e2257b8b3b949ddb27a65ce254521cf",
       "value": 7
      }
     },
     "2b3fe87be75e4e10b1ac472c01d3d71c": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "2bfcdcce67344a27a9167cc4616472d4": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "2d4c863278a748049184dda0bc941c3f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "2faf5132278443e98643a83334f0fa4b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "2ffc1fbf993f455f85bcd120c985cb45": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "305e2615a5384f39b65af634893dfca7": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_5ff36610098747d6b2650b5b201e4b4b",
       "outputs": [
        {
         "ename": "TypeError",
         "evalue": "Invalid dimensions for image data",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m<ipython-input-33-8c8290c93c3a>\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     17\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msubplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m5\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mi\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     18\u001b[0m         \u001b[0mdigit\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mimages\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 19\u001b[1;33m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdigit\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcmap\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbinary\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     20\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Index:{}, Label:{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfontsize\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m15\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, data, **kwargs)\u001b[0m\n\u001b[0;32m   2697\u001b[0m         \u001b[0mfilternorm\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilternorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mimlim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mimlim\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2698\u001b[0m         resample=resample, url=url, **({\"data\": data} if data is not\n\u001b[1;32m-> 2699\u001b[1;33m         None else {}), **kwargs)\n\u001b[0m\u001b[0;32m   2700\u001b[0m     \u001b[0msci\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m__ret\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2701\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0m__ret\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\__init__.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(ax, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1808\u001b[0m                         \u001b[1;34m\"the Matplotlib list!)\"\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mlabel_namer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1809\u001b[0m                         RuntimeWarning, stacklevel=2)\n\u001b[1;32m-> 1810\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1811\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1812\u001b[0m         inner.__doc__ = _add_data_doc(inner.__doc__,\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(self, X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, **kwargs)\u001b[0m\n\u001b[0;32m   5492\u001b[0m                               resample=resample, **kwargs)\n\u001b[0;32m   5493\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5494\u001b[1;33m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   5495\u001b[0m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_alpha\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0malpha\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5496\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_clip_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\image.py\u001b[0m in \u001b[0;36mset_data\u001b[1;34m(self, A)\u001b[0m\n\u001b[0;32m    636\u001b[0m         if not (self._A.ndim == 2\n\u001b[0;32m    637\u001b[0m                 or self._A.ndim == 3 and self._A.shape[-1] in [3, 4]):\n\u001b[1;32m--> 638\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Invalid dimensions for image data\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    639\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    640\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_A\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mTypeError\u001b[0m: Invalid dimensions for image data"
         ]
        }
       ]
      }
     },
     "3184a2de01a64b4db82a9e30b42ab434": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "31d43a9fcdcb4cbaaafc51204592b7c5": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "32152ffb82de417596da3eef61b84d30": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "3230896f551f4f2198439653da7ccada": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_b67d6f03d1a244a99d2c96df4e0013d1",
       "style": "IPY_MODEL_5bbc16eea432489db8ffd1e5288436a5"
      }
     },
     "331a5979d64d4eaab13d8eded7aa90ac": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "345337fa9c9642668b7ac55017b616a5": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "34b93d65b4f444bbbf35751f7c1b426b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "364bb7c6ab1c439aba6a2eef7f102e06": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_1d681d7c19db4b038faa3b90d3155fdf",
       "step": 1,
       "style": "IPY_MODEL_753c5666d6114b269a808d8f7e424b20",
       "value": 37
      }
     },
     "3682d0e06ace4d69bd0bf0963db10c9c": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "3819e7d6d6c54b4096bdb012eeccbe3f": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_9eaf1dc4ae734ab58420143d214530e8",
        "IPY_MODEL_71e4b1fe777a431f894edcbd38a0971d",
        "IPY_MODEL_55a0cfe62b624f47a620543005dd3aeb"
       ],
       "layout": "IPY_MODEL_c231d83a4a644017aa877c7c5c24a515"
      }
     },
     "39bd900c5eb245b1a685c879fa53678f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "3a69d4af166e4eacaa341262d31265b7": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "3cb2728b98af4b47b40c742167cdb6a3": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_72bb6e8995d34cdcb7b45fc6a1ead32a",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "3e3e2bc01d674572916e5e460876be4e": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "41312a6940e54bdcb39a645d8d273fb1": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "4197880989fd49e7b22f12a75d696665": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "423c985f40644a0b9344c6e4475ebabf": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_fe87646370024eff89b3e3c4ec4609bc",
       "style": "IPY_MODEL_7fdf4ef30725400a91ff170bd3489663"
      }
     },
     "42d29870fa814aaeb7450a0c89471d34": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_f12a2cb1d9394832bf40b9e2391212ff",
        "IPY_MODEL_736d65d332844fe98cd548bd55b2bb41",
        "IPY_MODEL_305e2615a5384f39b65af634893dfca7"
       ],
       "layout": "IPY_MODEL_c9b361ce58b24f54bdfc120f3f6ccd47"
      }
     },
     "4371aa9de0a04145953e25242327db9f": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_2faf5132278443e98643a83334f0fa4b",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        },
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        },
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "4519c2e1ebec47c3b2e4f03ce5f3f786": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "453bfef45bcc4908b9fdba2753914164": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "45ecea7cac0b43ab8b6c3ffc7d3fb76f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "45facfdbf03842b2afed506b99f467a5": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "46bf614ff93c4e3996bb7391e7aa9d44": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "476c88e3fc3f4be7ab381ad0083aace1": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_878b2e7740164c129d58be08dec459e3",
       "style": "IPY_MODEL_fab066c052834899b704b940927fdf8c"
      }
     },
     "4790d0cb9af94b169286989ebab78a02": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_31d43a9fcdcb4cbaaafc51204592b7c5",
       "step": 1,
       "style": "IPY_MODEL_ca6056d841f0473f852fd46d57227c37",
       "value": 20
      }
     },
     "4794f083622a4d10a42df49afe2bfd0f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4848c0fefd504447a7877758fbc2415a": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4867d4e77bf54411b0a39d405f4bd7af": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_81a0db803306440989d84ed5e9532348",
       "style": "IPY_MODEL_9c223da287ff49609aa7fcb52a7d795c"
      }
     },
     "488299c254644a5ea0965bb2ea696c23": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_3184a2de01a64b4db82a9e30b42ab434",
       "style": "IPY_MODEL_2b3fe87be75e4e10b1ac472c01d3d71c"
      }
     },
     "4a2d3bb0655c4255a4ef0acb04827a24": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4b0d4aa669034033810e5b75c7cd3c47": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4cf08d41d49e4d0b8db626c03fa05247": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4e2257b8b3b949ddb27a65ce254521cf": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "4ecd95dcaad449c79c5b700f0058b221": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "4ef29da78d724778988718ee14ed9e96": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_b99b050b6b7e417d8fe97b7bab398544",
       "style": "IPY_MODEL_f150cab4a2774cee9e4f3e65d9671101"
      }
     },
     "4f5773aa3ac342e49c6cbcef199de112": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_7230af683d9b4cca8b580c55e227d1d7",
       "style": "IPY_MODEL_6645e422a9a0454f99922fc45df96afe"
      }
     },
     "5089eacaf98447e28aca6a2e79244a1e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "511d82ade0a144b5acadad9b40638e04": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_3230896f551f4f2198439653da7ccada",
        "IPY_MODEL_56502aada6584a329c659fac7ced845a",
        "IPY_MODEL_f8e375b603444d4bb63a418240d81766"
       ],
       "layout": "IPY_MODEL_00c7d021fc0749a89f580d4f286830cb"
      }
     },
     "51a9705fbb26444897955b4ee1561910": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_7efca53b9c5a44daab0afcaaa9f76488",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "5345234c43d04c36934808e0dc5330ac": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "54684d51be044446817e26563631121e": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "55a0cfe62b624f47a620543005dd3aeb": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_46bf614ff93c4e3996bb7391e7aa9d44",
       "outputs": [
        {
         "name": "stdout",
         "output_type": "stream",
         "text": "7\n"
        }
       ]
      }
     },
     "56502aada6584a329c659fac7ced845a": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_a2d3c73beda94eb3bf47b7e2ae77b18e",
       "step": 1,
       "style": "IPY_MODEL_7933522d38614fcb949f0b5fde6b128c",
       "value": 7
      }
     },
     "57f5b0ed80224d40ad0bb8a807ee20a5": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "584a9614890d4dc0b8126b7c15860693": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "591651746a9c4d07a11be62250923043": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "59c1fd94f51b456abde984f61d866072": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "5bbc16eea432489db8ffd1e5288436a5": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "5ca79c1351ce4b35a47a9d483cbd8aa1": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 1,
       "layout": "IPY_MODEL_130ddb19822c483793ef93cf6784e1ec",
       "style": "IPY_MODEL_dd503225abf54de9910b6b2ac3282d01"
      }
     },
     "5cc6b49b30b64f37af54128a8696e143": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "5efb266431dc40ff8530ddffd3d980bc": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_0c985c0a9a834020b472fba00d4263b9",
        "IPY_MODEL_74045acdcd064c6a90f8590ba7e9acd7",
        "IPY_MODEL_21a382c120884dc4a4a6a81f7d80a244"
       ],
       "layout": "IPY_MODEL_4cf08d41d49e4d0b8db626c03fa05247"
      }
     },
     "5ff36610098747d6b2650b5b201e4b4b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "6015b3a721fc4fe1ab2112d2858af516": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_dabdba06427a46fa9a82f973abbff18d",
        "IPY_MODEL_e1246eb1cfb347bc88796dbf0d2c5d5a",
        "IPY_MODEL_079904e5f12948cd84187edcc132a0d4"
       ],
       "layout": "IPY_MODEL_45facfdbf03842b2afed506b99f467a5"
      }
     },
     "61ba612f43634e61aebd3a0fb6046ef0": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_20aef094b75243ffab1a2bea3b2b5ea4",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "6307dc9d17b749d98029169a773e644e": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_00c2e2fcea4249a1ba250b2e40ed50c1",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "6386d178aef84176a53efe20ccf266ae": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_7124d5e4d1884859b1036a54a3cbbb2b",
        "IPY_MODEL_364bb7c6ab1c439aba6a2eef7f102e06",
        "IPY_MODEL_9961e1f358dc4bbba23361708acf567b"
       ],
       "layout": "IPY_MODEL_78ac44866f554874b12f0d2ab60cb170"
      }
     },
     "63f0621888a147b78ff4551deea5b214": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "6404b8a2066547a7803fd35bd67b6694": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "65747f8948384668b9ad4bebc6734814": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_dd162009040c4021b2ec1622a8356ee0",
       "outputs": [
        {
         "ename": "TypeError",
         "evalue": "Invalid dimensions for image data",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m<ipython-input-32-b6dc27e6a614>\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     17\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msubplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m5\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mi\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     18\u001b[0m         \u001b[0mdigit\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mimages\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 19\u001b[1;33m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdigit\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcmap\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbinary\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     20\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Index:{}, Label:{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfontsize\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m15\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, data, **kwargs)\u001b[0m\n\u001b[0;32m   2697\u001b[0m         \u001b[0mfilternorm\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilternorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mimlim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mimlim\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2698\u001b[0m         resample=resample, url=url, **({\"data\": data} if data is not\n\u001b[1;32m-> 2699\u001b[1;33m         None else {}), **kwargs)\n\u001b[0m\u001b[0;32m   2700\u001b[0m     \u001b[0msci\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m__ret\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2701\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0m__ret\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\__init__.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(ax, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1808\u001b[0m                         \u001b[1;34m\"the Matplotlib list!)\"\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mlabel_namer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1809\u001b[0m                         RuntimeWarning, stacklevel=2)\n\u001b[1;32m-> 1810\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1811\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1812\u001b[0m         inner.__doc__ = _add_data_doc(inner.__doc__,\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(self, X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, **kwargs)\u001b[0m\n\u001b[0;32m   5492\u001b[0m                               resample=resample, **kwargs)\n\u001b[0;32m   5493\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5494\u001b[1;33m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   5495\u001b[0m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_alpha\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0malpha\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5496\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_clip_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\image.py\u001b[0m in \u001b[0;36mset_data\u001b[1;34m(self, A)\u001b[0m\n\u001b[0;32m    636\u001b[0m         if not (self._A.ndim == 2\n\u001b[0;32m    637\u001b[0m                 or self._A.ndim == 3 and self._A.shape[-1] in [3, 4]):\n\u001b[1;32m--> 638\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Invalid dimensions for image data\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    639\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    640\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_A\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mTypeError\u001b[0m: Invalid dimensions for image data"
         ]
        }
       ]
      }
     },
     "6645e422a9a0454f99922fc45df96afe": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "6730b82f33c247f6acd37320bc23ce0e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "683a50a59bc046eb8fed5531e2fdda9a": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "6981f6177d0f45ba871f2d76e29d6bcb": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "6be70605d0404960b61a1e84670292c8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_9a87723e788449b4888257c431823c8e",
       "style": "IPY_MODEL_c21058ded0aa48969588109acbde316f"
      }
     },
     "6c1b6d87dff249388383bf55b8e0ec05": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "6cc77f33828c4be186e173b172558bf2": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "7124d5e4d1884859b1036a54a3cbbb2b": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 1,
       "layout": "IPY_MODEL_e1b984e54bc74027a7f834acf77e4bf4",
       "style": "IPY_MODEL_bd1e1afa3a5f429b82ef11ea8dbd4c80"
      }
     },
     "7165a1a6d7104e94bb306b4ff1d41b7c": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "71e4b1fe777a431f894edcbd38a0971d": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_a8327ad4af6248a2885d13ca26fa3bd2",
       "step": 1,
       "style": "IPY_MODEL_09d823911add4064b574339ac7e9e919",
       "value": 7
      }
     },
     "721b75acd603439f967a47a0e2d43db6": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_08bf79865a2a4f9d8dd36f731de2eae3",
        "IPY_MODEL_c65cb220664a41309a0eadb88de66f35",
        "IPY_MODEL_fc5ec0d679504ba1919bd48a02f5bc90"
       ],
       "layout": "IPY_MODEL_1550c9b1e9d44b9b91f8edb789cefc21"
      }
     },
     "7230af683d9b4cca8b580c55e227d1d7": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "72bb6e8995d34cdcb7b45fc6a1ead32a": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "736d65d332844fe98cd548bd55b2bb41": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_9b0c9d0214a8470e8f6b39db325ff3b6",
       "step": 1,
       "style": "IPY_MODEL_8135e1c1005d40629e4e32e984245150",
       "value": 7
      }
     },
     "74045acdcd064c6a90f8590ba7e9acd7": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_1977a091ce4e45b89d59d5c037f3ea7b",
       "step": 1,
       "style": "IPY_MODEL_86a3b3ccef0344ba9746cac7417367b6",
       "value": 7
      }
     },
     "753c5666d6114b269a808d8f7e424b20": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "75bfde70327e4543b91ff5bde6b1cefa": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_5ca79c1351ce4b35a47a9d483cbd8aa1",
        "IPY_MODEL_ed7b09e9a7824f78b28ac6039f32ad71",
        "IPY_MODEL_1b9ac7a01d104dffa0fb6ac2caf86ae8"
       ],
       "layout": "IPY_MODEL_82b60ba9299d4562876444187c0567a7"
      }
     },
     "7686d452539245a8981910ea9744e659": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_9d0d7b294698474aabd134df5ad11cd4",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "76b55bd970e64646921b3b6f2a064620": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "78ac44866f554874b12f0d2ab60cb170": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "7933522d38614fcb949f0b5fde6b128c": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "7ba7cb4bbe294db5902c55549e4397ba": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_1863cdb927484671a13bc2eb3e3888d8",
        "IPY_MODEL_1fe1ff51f21c4c668e1a1e59338d5235",
        "IPY_MODEL_6307dc9d17b749d98029169a773e644e"
       ],
       "layout": "IPY_MODEL_591651746a9c4d07a11be62250923043"
      }
     },
     "7d80719ab48548439f1b5fdadbb56d20": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_4867d4e77bf54411b0a39d405f4bd7af",
        "IPY_MODEL_b98c41251e6142ce835dd2c0b6ba2142",
        "IPY_MODEL_19a1a4c07cc14d34910e28c5706218b1"
       ],
       "layout": "IPY_MODEL_2881ff2455614d48b61745237157e7ae"
      }
     },
     "7efca53b9c5a44daab0afcaaa9f76488": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "7f3e469010d94a43a0f3fab0e88e6674": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_3e3e2bc01d674572916e5e460876be4e",
       "style": "IPY_MODEL_17ea7648990c4d758a5477ef85a6ccb0"
      }
     },
     "7fdf4ef30725400a91ff170bd3489663": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "8135e1c1005d40629e4e32e984245150": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "81a0db803306440989d84ed5e9532348": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "81d26b91e042428090a2d3c66036d292": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "81e092023f7943b5863949d9c1e3d6d2": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_913ab6e949024f35865a7b108f27dc87",
       "outputs": [
        {
         "ename": "NameError",
         "evalue": "name 'train_images' is not defined",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32mD:\\Dropbox\\Work\\Web\\business-analytics\\docs\\machine_learning\\loadmlfuncs.py\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     13\u001b[0m     \u001b[0mspan\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m5\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     14\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m==\u001b[0m\u001b[1;34m'train'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 15\u001b[1;33m         \u001b[1;32mif\u001b[0m \u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mspan\u001b[0m\u001b[1;33m<\u001b[0m\u001b[0mtrain_images\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     16\u001b[0m             \u001b[0mimages\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtrain_images\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     17\u001b[0m             \u001b[0mlabels\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtrain_labels\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mNameError\u001b[0m: name 'train_images' is not defined"
         ]
        }
       ]
      }
     },
     "826811a6a51244e49bd0ff7852d54159": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_476c88e3fc3f4be7ab381ad0083aace1",
        "IPY_MODEL_d7745bd242224a988a58efa35e233219",
        "IPY_MODEL_65747f8948384668b9ad4bebc6734814"
       ],
       "layout": "IPY_MODEL_4a2d3bb0655c4255a4ef0acb04827a24"
      }
     },
     "82b60ba9299d4562876444187c0567a7": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "86a3b3ccef0344ba9746cac7417367b6": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "878b2e7740164c129d58be08dec459e3": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "8957a6314e084f20b1309e0dfdae959f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "89c4ed731f3247e187dcd426f63ae484": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "8d4ef1166513401aa5b1bc2e9a9e9644": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_6981f6177d0f45ba871f2d76e29d6bcb",
       "step": 1,
       "style": "IPY_MODEL_b0019fe65a4f49e6a352706903e8b01d",
       "value": 7
      }
     },
     "8da9cbfbbc1f4cd880376f3340918c64": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "8fad9b56b6b0444394e2ee2ce3dbba17": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_6be70605d0404960b61a1e84670292c8",
        "IPY_MODEL_c1db949ba9934687a49195fb093d25b8",
        "IPY_MODEL_61ba612f43634e61aebd3a0fb6046ef0"
       ],
       "layout": "IPY_MODEL_c718eaf299b648969237ce08346e0c26"
      }
     },
     "913ab6e949024f35865a7b108f27dc87": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "948066a84daf4d2db91df70a84729a1e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_331a5979d64d4eaab13d8eded7aa90ac",
       "style": "IPY_MODEL_1c1535a7cad445a2a41ec14b57b1048c"
      }
     },
     "9961e1f358dc4bbba23361708acf567b": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_2d4c863278a748049184dda0bc941c3f",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "9a87723e788449b4888257c431823c8e": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "9b0c9d0214a8470e8f6b39db325ff3b6": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "9c223da287ff49609aa7fcb52a7d795c": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "9d0d7b294698474aabd134df5ad11cd4": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "9e4380dd6afb4854a4acf0efd46a227e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_4ecd95dcaad449c79c5b700f0058b221",
       "step": 1,
       "style": "IPY_MODEL_bd441e2e093542a08d2f9b3911dca84d",
       "value": 7
      }
     },
     "9eaf1dc4ae734ab58420143d214530e8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_d59442b429044be98e97b289d153849b",
       "style": "IPY_MODEL_41312a6940e54bdcb39a645d8d273fb1"
      }
     },
     "9f01963e914e406b9b85c18e7b2bf133": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "a2d3c73beda94eb3bf47b7e2ae77b18e": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "a8327ad4af6248a2885d13ca26fa3bd2": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "abc5241bd20a4104b6905e027bb5b1bf": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "affa269ad75b474799eda2bc0c4048dd": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "b0019fe65a4f49e6a352706903e8b01d": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "b3173158918a4abe82139893f8e9e86e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "b3367d588b1d4853adbb866095514389": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_488299c254644a5ea0965bb2ea696c23",
        "IPY_MODEL_2b115a7c92e24b03bd788de53cd0deaa",
        "IPY_MODEL_4371aa9de0a04145953e25242327db9f"
       ],
       "layout": "IPY_MODEL_45ecea7cac0b43ab8b6c3ffc7d3fb76f"
      }
     },
     "b371e5b9c7d64331bc40c99ee0a01134": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_7f3e469010d94a43a0f3fab0e88e6674",
        "IPY_MODEL_db40f904bec54ffaa6d2a9756b1ab7d3",
        "IPY_MODEL_edf5a5de932d4470a84a562d20ffdda4"
       ],
       "layout": "IPY_MODEL_18e8908201d942c68622f497a6a06c55"
      }
     },
     "b67d6f03d1a244a99d2c96df4e0013d1": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "b98c41251e6142ce835dd2c0b6ba2142": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_59c1fd94f51b456abde984f61d866072",
       "step": 1,
       "style": "IPY_MODEL_c72ede9058154d0bb0346aac7bb5b6d5",
       "value": 7
      }
     },
     "b99b050b6b7e417d8fe97b7bab398544": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "bb0d1743d1e94df2b9b1275823ae6da9": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_76b55bd970e64646921b3b6f2a064620",
       "style": "IPY_MODEL_04b2c1c8d5814b3b96910f6318b694fc"
      }
     },
     "bb3b5071f4aa476499a543056a20ace8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_948066a84daf4d2db91df70a84729a1e",
        "IPY_MODEL_4790d0cb9af94b169286989ebab78a02",
        "IPY_MODEL_51a9705fbb26444897955b4ee1561910"
       ],
       "layout": "IPY_MODEL_683a50a59bc046eb8fed5531e2fdda9a"
      }
     },
     "bb8de73e13e347ecb53975dbffcb2e91": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "bbddf6aba8c5408ba0afdcea3ce66662": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "bd1e1afa3a5f429b82ef11ea8dbd4c80": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "bd441e2e093542a08d2f9b3911dca84d": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "be2b75873f6848269487653ccbae4dfa": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "bf08792c9a88453fa78242878858cbb4": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "c01cab0af10d47b38652ffb80a8e8ed8": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "c0724b2665764538896f23d90097a9b4": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "c1db949ba9934687a49195fb093d25b8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_fc2ff9d7f9bf44e0a09f224887fc5f62",
       "step": 1,
       "style": "IPY_MODEL_9f01963e914e406b9b85c18e7b2bf133",
       "value": 7
      }
     },
     "c21058ded0aa48969588109acbde316f": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "c231d83a4a644017aa877c7c5c24a515": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "c2bc86d3a7d54c739d1624862c57a52a": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_12597650ff034e3183cd86eaa9706e43",
       "step": 1,
       "style": "IPY_MODEL_ce20bc2798e546aab3bbd60b616ecda8",
       "value": 7
      }
     },
     "c65cb220664a41309a0eadb88de66f35": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_14034ecacb884e2ba54d506875da6a86",
       "step": 1,
       "style": "IPY_MODEL_dc1725b9b93341d68c2e9e49e5385c1e",
       "value": 7
      }
     },
     "c718eaf299b648969237ce08346e0c26": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "c72ede9058154d0bb0346aac7bb5b6d5": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "c9b361ce58b24f54bdfc120f3f6ccd47": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "ca6056d841f0473f852fd46d57227c37": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "cad7e4bcc3804790ad5722afaa19a2f2": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "ce20bc2798e546aab3bbd60b616ecda8": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "d05babe4136f40a4ac996ceeb1554037": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_c0724b2665764538896f23d90097a9b4",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 1440x288 with 5 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "d0cf46cdf0d740fa83350c3093414e17": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "d59442b429044be98e97b289d153849b": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "d5f5464eec0e43eb84db9e867d06f9e3": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "d7745bd242224a988a58efa35e233219": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_bf08792c9a88453fa78242878858cbb4",
       "step": 1,
       "style": "IPY_MODEL_abc5241bd20a4104b6905e027bb5b1bf",
       "value": 7
      }
     },
     "d85dab25dcd342aab8136eb59c489799": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_423c985f40644a0b9344c6e4475ebabf",
        "IPY_MODEL_dceae78d83394897b49f60dac8e50472",
        "IPY_MODEL_7686d452539245a8981910ea9744e659"
       ],
       "layout": "IPY_MODEL_0315f967b7934712ac027e7c595b98dc"
      }
     },
     "da42c8e581b446c09491b33fe3d9700f": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "dabdba06427a46fa9a82f973abbff18d": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_5345234c43d04c36934808e0dc5330ac",
       "style": "IPY_MODEL_6730b82f33c247f6acd37320bc23ce0e"
      }
     },
     "db40f904bec54ffaa6d2a9756b1ab7d3": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_32152ffb82de417596da3eef61b84d30",
       "step": 1,
       "style": "IPY_MODEL_e71d0f7cf9114a1cb2a2062e58f73e70",
       "value": 7
      }
     },
     "dc1725b9b93341d68c2e9e49e5385c1e": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "dceae78d83394897b49f60dac8e50472": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_81d26b91e042428090a2d3c66036d292",
       "step": 1,
       "style": "IPY_MODEL_e0e338bd7c6e4f47840bc7a547f165e4",
       "value": 7
      }
     },
     "dd162009040c4021b2ec1622a8356ee0": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "dd503225abf54de9910b6b2ac3282d01": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "dd5bf12baab94089909e23f67a479789": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_0ee5ce8bc70747f48657e1d27692916f",
        "IPY_MODEL_22b375bb048e434dadcbdd4aecd7895a",
        "IPY_MODEL_3cb2728b98af4b47b40c742167cdb6a3"
       ],
       "layout": "IPY_MODEL_54684d51be044446817e26563631121e"
      }
     },
     "dd6302e8933b4eaeba40db8c4a7a5768": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "de24cf0b57bc409f9467a51b4b878663": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "e0e338bd7c6e4f47840bc7a547f165e4": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "e1246eb1cfb347bc88796dbf0d2c5d5a": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_c01cab0af10d47b38652ffb80a8e8ed8",
       "step": 1,
       "style": "IPY_MODEL_453bfef45bcc4908b9fdba2753914164",
       "value": 1000
      }
     },
     "e1b984e54bc74027a7f834acf77e4bf4": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "e71d0f7cf9114a1cb2a2062e58f73e70": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "ec6efca69df94ca08be9a7ac451e2b60": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_4f5773aa3ac342e49c6cbcef199de112",
        "IPY_MODEL_01ea1d8b14344d1bae3f0ec7605d08ab",
        "IPY_MODEL_d05babe4136f40a4ac996ceeb1554037"
       ],
       "layout": "IPY_MODEL_6cc77f33828c4be186e173b172558bf2"
      }
     },
     "ed34214dc73e4f29964958c078ca1b45": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "ed7b09e9a7824f78b28ac6039f32ad71": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "IntTextModel",
      "state": {
       "description": "Index:",
       "layout": "IPY_MODEL_584a9614890d4dc0b8126b7c15860693",
       "step": 1,
       "style": "IPY_MODEL_2ffc1fbf993f455f85bcd120c985cb45",
       "value": 8
      }
     },
     "edf5a5de932d4470a84a562d20ffdda4": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_4794f083622a4d10a42df49afe2bfd0f",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        },
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        },
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "eef42ab6008642da9e826d35d40fab29": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_17dd22a77be04c86b54f068355a23b1f",
        "IPY_MODEL_9e4380dd6afb4854a4acf0efd46a227e",
        "IPY_MODEL_0e267085d75a4770b279d8dc0d696650"
       ],
       "layout": "IPY_MODEL_4b0d4aa669034033810e5b75c7cd3c47"
      }
     },
     "ef6c009640b64f31a506936690e23692": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "f12a2cb1d9394832bf40b9e2391212ff": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "RadioButtonsModel",
      "state": {
       "_options_labels": [
        "train",
        "test"
       ],
       "description": "Data:",
       "index": 0,
       "layout": "IPY_MODEL_bbddf6aba8c5408ba0afdcea3ce66662",
       "style": "IPY_MODEL_b3173158918a4abe82139893f8e9e86e"
      }
     },
     "f150cab4a2774cee9e4f3e65d9671101": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "f5c32f6a88874e3b92be6d92d1800b78": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_4ef29da78d724778988718ee14ed9e96",
        "IPY_MODEL_c2bc86d3a7d54c739d1624862c57a52a",
        "IPY_MODEL_0cb2219d39b34f9eba1c52a33d85830b"
       ],
       "layout": "IPY_MODEL_bb8de73e13e347ecb53975dbffcb2e91"
      }
     },
     "f648fde6eeb54f149f284c198eaf6e88": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "VBoxModel",
      "state": {
       "_dom_classes": [
        "widget-interact"
       ],
       "children": [
        "IPY_MODEL_16eb75aed3a94d73bb78f1013a6df7c4",
        "IPY_MODEL_0f724e736e35441585282559a145abfd",
        "IPY_MODEL_1f6325aee9ad4d81bbf5cdb586b352f2"
       ],
       "layout": "IPY_MODEL_7165a1a6d7104e94bb306b4ff1d41b7c"
      }
     },
     "f8e375b603444d4bb63a418240d81766": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_39bd900c5eb245b1a685c879fa53678f",
       "outputs": [
        {
         "ename": "TypeError",
         "evalue": "Invalid dimensions for image data",
         "output_type": "error",
         "traceback": [
          "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
          "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\ipywidgets\\widgets\\interaction.py\u001b[0m in \u001b[0;36mupdate\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m                     \u001b[0mvalue\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_interact_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    250\u001b[0m                     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mwidget\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_kwarg\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 251\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    252\u001b[0m                 \u001b[0mshow_inline_matplotlib_plots\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    253\u001b[0m                 \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mauto_display\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m<ipython-input-21-b6dc27e6a614>\u001b[0m in \u001b[0;36mshowimg\u001b[1;34m(data, idx)\u001b[0m\n\u001b[0;32m     17\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msubplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m5\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mi\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     18\u001b[0m         \u001b[0mdigit\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mimages\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 19\u001b[1;33m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdigit\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcmap\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbinary\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     20\u001b[0m         \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Index:{}, Label:{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0midx\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfontsize\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m15\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     21\u001b[0m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, data, **kwargs)\u001b[0m\n\u001b[0;32m   2697\u001b[0m         \u001b[0mfilternorm\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilternorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mimlim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mimlim\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2698\u001b[0m         resample=resample, url=url, **({\"data\": data} if data is not\n\u001b[1;32m-> 2699\u001b[1;33m         None else {}), **kwargs)\n\u001b[0m\u001b[0;32m   2700\u001b[0m     \u001b[0msci\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m__ret\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2701\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0m__ret\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\__init__.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(ax, data, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1808\u001b[0m                         \u001b[1;34m\"the Matplotlib list!)\"\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mlabel_namer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1809\u001b[0m                         RuntimeWarning, stacklevel=2)\n\u001b[1;32m-> 1810\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1811\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1812\u001b[0m         inner.__doc__ = _add_data_doc(inner.__doc__,\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(self, X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, **kwargs)\u001b[0m\n\u001b[0;32m   5492\u001b[0m                               resample=resample, **kwargs)\n\u001b[0;32m   5493\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5494\u001b[1;33m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   5495\u001b[0m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_alpha\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0malpha\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5496\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_clip_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;32m~\\AppData\\Local\\Continuum\\anaconda3\\envs\\bzan\\lib\\site-packages\\matplotlib\\image.py\u001b[0m in \u001b[0;36mset_data\u001b[1;34m(self, A)\u001b[0m\n\u001b[0;32m    636\u001b[0m         if not (self._A.ndim == 2\n\u001b[0;32m    637\u001b[0m                 or self._A.ndim == 3 and self._A.shape[-1] in [3, 4]):\n\u001b[1;32m--> 638\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Invalid dimensions for image data\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    639\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    640\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_A\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
          "\u001b[1;31mTypeError\u001b[0m: Invalid dimensions for image data"
         ]
        }
       ]
      }
     },
     "fab066c052834899b704b940927fdf8c": {
      "model_module": "@jupyter-widgets/controls",
      "model_module_version": "1.4.0",
      "model_name": "DescriptionStyleModel",
      "state": {
       "description_width": ""
      }
     },
     "fc2ff9d7f9bf44e0a09f224887fc5f62": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     },
     "fc5ec0d679504ba1919bd48a02f5bc90": {
      "model_module": "@jupyter-widgets/output",
      "model_module_version": "1.0.0",
      "model_name": "OutputModel",
      "state": {
       "layout": "IPY_MODEL_6c1b6d87dff249388383bf55b8e0ec05",
       "outputs": [
        {
         "data": {
          "image/png": "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\n",
          "text/plain": "<Figure size 432x288 with 1 Axes>"
         },
         "metadata": {
          "needs_background": "light"
         },
         "output_type": "display_data"
        }
       ]
      }
     },
     "fe87646370024eff89b3e3c4ec4609bc": {
      "model_module": "@jupyter-widgets/base",
      "model_module_version": "1.1.0",
      "model_name": "LayoutModel",
      "state": {}
     }
    },
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}