mlpractical/notebooks/Plot_Results.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import sys\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "%matplotlib inline\n",
    "plt.style.use('ggplot')\n",
    "experiment_dir = '/home/anton/uni/MLP/mlpractical' #Replace this with your path to the mlpractical directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def collect_experiment_dicts(target_dir, test_flag=False):\n",
    "    experiment_dicts = dict()\n",
    "    for subdir, dir, files in os.walk(target_dir):\n",
    "        for file in files:\n",
    "            filepath = None\n",
    "            if not test_flag:\n",
    "                if file == 'summary.csv':\n",
    "                    filepath = os.path.join(subdir, file)\n",
    "            \n",
    "            elif test_flag:\n",
    "                if file == 'test_summary.csv':\n",
    "                    filepath = os.path.join(subdir, file)\n",
    "            \n",
    "            if filepath is not None:\n",
    "                \n",
    "                with open(filepath, 'r') as read_file:\n",
    "                    lines = read_file.readlines()\n",
    "                    \n",
    "                current_experiment_dict = {key: [] for key in lines[0].replace('\\n', '').split(',')}\n",
    "                idx_to_key = {idx: key for idx, key in enumerate(lines[0].replace('\\n', '').split(','))}\n",
    "                \n",
    "                for line in lines[1:]:\n",
    "                    for idx, value in enumerate(line.replace('\\n', '').split(',')):\n",
    "                        current_experiment_dict[idx_to_key[idx]].append(float(value))\n",
    "                \n",
    "                experiment_dicts[subdir.split('/')[-2]] = current_experiment_dict\n",
    "                \n",
    "    return experiment_dicts\n",
    "                \n",
    "            "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "VGG_08 ['train_acc', 'train_loss', 'val_acc', 'val_loss']\n",
      "VGG_38 ['train_acc', 'train_loss', 'val_acc', 'val_loss']\n"
     ]
    }
   ],
   "source": [
    "result_dict = collect_experiment_dicts(target_dir=experiment_dir)\n",
    "for key, value in result_dict.items():\n",
    "    print(key, list(value.keys()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "plt.style.use('ggplot')\n",
    "\n",
    "def plot_result_graphs(plot_name, stats, keys_to_plot, notebook=True):\n",
    "    \n",
    "    fig_1 = plt.figure(figsize=(8, 4))\n",
    "    ax_1 = fig_1.add_subplot(111)\n",
    "    for name in keys_to_plot:\n",
    "        for k in ['train_loss', 'val_loss']:\n",
    "            item = stats[name][k]\n",
    "            ax_1.plot(np.arange(0, len(item)), \n",
    "                      item, label='{}_{}'.format(name, k))\n",
    "            \n",
    "    ax_1.legend(loc=0)\n",
    "    ax_1.set_ylabel('Loss')\n",
    "    ax_1.set_xlabel('Epoch number')\n",
    "\n",
    "    # Plot the change in the validation and training set accuracy over training.\n",
    "    fig_2 = plt.figure(figsize=(8, 4))\n",
    "    ax_2 = fig_2.add_subplot(111)\n",
    "    for name in keys_to_plot:\n",
    "        for k in ['train_acc', 'val_acc']:\n",
    "            item = stats[name][k]\n",
    "            ax_2.plot(np.arange(0, len(item)), \n",
    "                      item, label='{}_{}'.format(name, k))\n",
    "            \n",
    "    ax_2.legend(loc=0)\n",
    "    ax_2.set_ylabel('Accuracy')\n",
    "    ax_2.set_xlabel('Epoch number')\n",
    "    \n",
    "    fig_1.savefig('../data/{}_loss_performance.pdf'.format(plot_name), dpi=None, facecolor='w', edgecolor='w',\n",
    "        orientation='portrait', format='pdf',\n",
    "        transparent=False, bbox_inches=None, pad_inches=0.1,\n",
    "         metadata=None)\n",
    "    \n",
    "    fig_2.savefig('../data/{}_accuracy_performance.pdf'.format(plot_name), dpi=None, facecolor='w', edgecolor='w',\n",
    "        orientation='portrait', format='pdf',\n",
    "        transparent=False, bbox_inches=None, pad_inches=0.1,\n",
    "        metadata=None)\n",
    "    \n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_result_graphs('problem_model', result_dict, keys_to_plot=['VGG_38', 'VGG_08'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'VGG_08': {'train_acc': [0.010694736842105264,\n",
       "   0.03562105263157895,\n",
       "   0.0757684210526316,\n",
       "   0.10734736842105265,\n",
       "   0.13741052631578948,\n",
       "   0.16888421052631578,\n",
       "   0.1941263157894737,\n",
       "   0.21861052631578948,\n",
       "   0.24134736842105264,\n",
       "   0.26399999999999996,\n",
       "   0.27898947368421056,\n",
       "   0.29532631578947366,\n",
       "   0.31138947368421044,\n",
       "   0.3236842105263158,\n",
       "   0.33486315789473686,\n",
       "   0.3462526315789474,\n",
       "   0.35381052631578946,\n",
       "   0.36157894736842106,\n",
       "   0.36774736842105266,\n",
       "   0.37753684210526317,\n",
       "   0.38597894736842114,\n",
       "   0.3912421052631579,\n",
       "   0.39840000000000003,\n",
       "   0.4036,\n",
       "   0.4105263157894737,\n",
       "   0.41501052631578944,\n",
       "   0.4193263157894737,\n",
       "   0.4211578947368421,\n",
       "   0.4260842105263159,\n",
       "   0.4313684210526315,\n",
       "   0.4370526315789474,\n",
       "   0.439642105263158,\n",
       "   0.4440842105263158,\n",
       "   0.44696842105263157,\n",
       "   0.4518105263157895,\n",
       "   0.45298947368421055,\n",
       "   0.4602105263157895,\n",
       "   0.46023157894736844,\n",
       "   0.46101052631578954,\n",
       "   0.46774736842105263,\n",
       "   0.4671157894736842,\n",
       "   0.4698105263157895,\n",
       "   0.4738736842105264,\n",
       "   0.47541052631578945,\n",
       "   0.48,\n",
       "   0.48456842105263154,\n",
       "   0.4857263157894737,\n",
       "   0.4887578947368421,\n",
       "   0.49035789473684216,\n",
       "   0.4908421052631579,\n",
       "   0.4939368421052632,\n",
       "   0.49924210526315793,\n",
       "   0.49677894736842104,\n",
       "   0.5008842105263157,\n",
       "   0.5,\n",
       "   0.5030736842105263,\n",
       "   0.505578947368421,\n",
       "   0.5090315789473684,\n",
       "   0.512042105263158,\n",
       "   0.5142736842105263,\n",
       "   0.5128421052631579,\n",
       "   0.518042105263158,\n",
       "   0.5182315789473684,\n",
       "   0.5192842105263158,\n",
       "   0.5217894736842105,\n",
       "   0.5229684210526316,\n",
       "   0.5227578947368421,\n",
       "   0.5245894736842105,\n",
       "   0.5262315789473684,\n",
       "   0.5278526315789474,\n",
       "   0.527157894736842,\n",
       "   0.5299578947368421,\n",
       "   0.5313052631578947,\n",
       "   0.5338315789473685,\n",
       "   0.5336000000000001,\n",
       "   0.5354736842105263,\n",
       "   0.5397894736842105,\n",
       "   0.5386526315789474,\n",
       "   0.5376631578947368,\n",
       "   0.5384842105263159,\n",
       "   0.5380842105263157,\n",
       "   0.5393473684210528,\n",
       "   0.5415157894736843,\n",
       "   0.5394947368421052,\n",
       "   0.5429052631578948,\n",
       "   0.5452421052631579,\n",
       "   0.5436210526315789,\n",
       "   0.5437684210526316,\n",
       "   0.546357894736842,\n",
       "   0.5485052631578946,\n",
       "   0.5466736842105263,\n",
       "   0.547621052631579,\n",
       "   0.5480421052631579,\n",
       "   0.5468421052631579,\n",
       "   0.5493894736842105,\n",
       "   0.5490736842105263,\n",
       "   0.5514736842105264,\n",
       "   0.5489263157894737,\n",
       "   0.5494947368421053,\n",
       "   0.5516842105263158,\n",
       "   0.552442105263158],\n",
       "  'train_loss': [4.827323,\n",
       "   4.3888855,\n",
       "   3.998175,\n",
       "   3.784943,\n",
       "   3.6023798,\n",
       "   3.4196754,\n",
       "   3.2674048,\n",
       "   3.139925,\n",
       "   3.0145736,\n",
       "   2.9004965,\n",
       "   2.815607,\n",
       "   2.7256868,\n",
       "   2.6567938,\n",
       "   2.595405,\n",
       "   2.5434496,\n",
       "   2.5021079,\n",
       "   2.4609485,\n",
       "   2.4152951,\n",
       "   2.382958,\n",
       "   2.3510027,\n",
       "   2.319616,\n",
       "   2.294115,\n",
       "   2.2598042,\n",
       "   2.2318766,\n",
       "   2.2035582,\n",
       "   2.1830406,\n",
       "   2.158597,\n",
       "   2.148888,\n",
       "   2.1250536,\n",
       "   2.107519,\n",
       "   2.0837262,\n",
       "   2.0691078,\n",
       "   2.046351,\n",
       "   2.0330904,\n",
       "   2.0200553,\n",
       "   2.0069249,\n",
       "   1.9896894,\n",
       "   1.9788533,\n",
       "   1.9693571,\n",
       "   1.9547894,\n",
       "   1.9390026,\n",
       "   1.924038,\n",
       "   1.9161719,\n",
       "   1.9033127,\n",
       "   1.8961077,\n",
       "   1.8838875,\n",
       "   1.8711865,\n",
       "   1.8590263,\n",
       "   1.8479114,\n",
       "   1.845268,\n",
       "   1.8336699,\n",
       "   1.8237538,\n",
       "   1.8111013,\n",
       "   1.8031327,\n",
       "   1.8026625,\n",
       "   1.792004,\n",
       "   1.7810374,\n",
       "   1.7691813,\n",
       "   1.7633294,\n",
       "   1.7549652,\n",
       "   1.7518128,\n",
       "   1.7420768,\n",
       "   1.7321203,\n",
       "   1.7264535,\n",
       "   1.7245325,\n",
       "   1.7184331,\n",
       "   1.7116771,\n",
       "   1.7009526,\n",
       "   1.6991171,\n",
       "   1.6958193,\n",
       "   1.6907407,\n",
       "   1.6808176,\n",
       "   1.676356,\n",
       "   1.6731659,\n",
       "   1.662152,\n",
       "   1.6638054,\n",
       "   1.6575475,\n",
       "   1.6595734,\n",
       "   1.6536722,\n",
       "   1.6495628,\n",
       "   1.6488388,\n",
       "   1.6408547,\n",
       "   1.632917,\n",
       "   1.6340653,\n",
       "   1.6340532,\n",
       "   1.6246406,\n",
       "   1.6288266,\n",
       "   1.6240481,\n",
       "   1.6208181,\n",
       "   1.6164333,\n",
       "   1.6169226,\n",
       "   1.6159856,\n",
       "   1.6175526,\n",
       "   1.6149833,\n",
       "   1.6063902,\n",
       "   1.6096952,\n",
       "   1.6084315,\n",
       "   1.6069487,\n",
       "   1.6030664,\n",
       "   1.6043342,\n",
       "   1.6039867],\n",
       "  'val_acc': [0.024800000000000003,\n",
       "   0.0604,\n",
       "   0.09480000000000001,\n",
       "   0.12159999999999999,\n",
       "   0.15439999999999998,\n",
       "   0.1864,\n",
       "   0.20720000000000002,\n",
       "   0.22880000000000003,\n",
       "   0.24760000000000001,\n",
       "   0.2552,\n",
       "   0.2764,\n",
       "   0.2968,\n",
       "   0.3016,\n",
       "   0.322,\n",
       "   0.3176,\n",
       "   0.33159999999999995,\n",
       "   0.342,\n",
       "   0.34119999999999995,\n",
       "   0.3332,\n",
       "   0.36160000000000003,\n",
       "   0.3608,\n",
       "   0.3732,\n",
       "   0.3716,\n",
       "   0.37439999999999996,\n",
       "   0.3772,\n",
       "   0.3876,\n",
       "   0.37800000000000006,\n",
       "   0.38160000000000005,\n",
       "   0.39840000000000003,\n",
       "   0.4044,\n",
       "   0.398,\n",
       "   0.41200000000000003,\n",
       "   0.4096,\n",
       "   0.4104,\n",
       "   0.4244,\n",
       "   0.42719999999999997,\n",
       "   0.4204,\n",
       "   0.4244,\n",
       "   0.4128,\n",
       "   0.4204,\n",
       "   0.4244,\n",
       "   0.424,\n",
       "   0.43,\n",
       "   0.4463999999999999,\n",
       "   0.44439999999999996,\n",
       "   0.43079999999999996,\n",
       "   0.44920000000000004,\n",
       "   0.44799999999999995,\n",
       "   0.4428,\n",
       "   0.4436,\n",
       "   0.4548,\n",
       "   0.4548,\n",
       "   0.44240000000000007,\n",
       "   0.4548,\n",
       "   0.458,\n",
       "   0.4596,\n",
       "   0.45679999999999993,\n",
       "   0.4444000000000001,\n",
       "   0.4616,\n",
       "   0.4464,\n",
       "   0.4656,\n",
       "   0.46,\n",
       "   0.45960000000000006,\n",
       "   0.46279999999999993,\n",
       "   0.46399999999999997,\n",
       "   0.46679999999999994,\n",
       "   0.4604,\n",
       "   0.4692,\n",
       "   0.4700000000000001,\n",
       "   0.4708,\n",
       "   0.4736,\n",
       "   0.4715999999999999,\n",
       "   0.47239999999999993,\n",
       "   0.47839999999999994,\n",
       "   0.4672,\n",
       "   0.4692,\n",
       "   0.4768,\n",
       "   0.4824,\n",
       "   0.4816,\n",
       "   0.47600000000000003,\n",
       "   0.478,\n",
       "   0.48,\n",
       "   0.4828,\n",
       "   0.4776,\n",
       "   0.47759999999999997,\n",
       "   0.48119999999999996,\n",
       "   0.4864,\n",
       "   0.48279999999999995,\n",
       "   0.4804,\n",
       "   0.47839999999999994,\n",
       "   0.47800000000000004,\n",
       "   0.4828,\n",
       "   0.48560000000000003,\n",
       "   0.48119999999999996,\n",
       "   0.4835999999999999,\n",
       "   0.48120000000000007,\n",
       "   0.4867999999999999,\n",
       "   0.4831999999999999,\n",
       "   0.49079999999999996,\n",
       "   0.486,\n",
       "   0.48480000000000006],\n",
       "  'val_loss': [4.5659676,\n",
       "   4.136276,\n",
       "   3.8678854,\n",
       "   3.6687074,\n",
       "   3.4829779,\n",
       "   3.3093607,\n",
       "   3.2223148,\n",
       "   3.1171055,\n",
       "   3.0554724,\n",
       "   2.9390912,\n",
       "   2.9205213,\n",
       "   2.7410471,\n",
       "   2.7083752,\n",
       "   2.665904,\n",
       "   2.688214,\n",
       "   2.648656,\n",
       "   2.5658453,\n",
       "   2.5403407,\n",
       "   2.6936982,\n",
       "   2.4663532,\n",
       "   2.4559999,\n",
       "   2.3644555,\n",
       "   2.4516551,\n",
       "   2.4189563,\n",
       "   2.3899698,\n",
       "   2.3215945,\n",
       "   2.3831298,\n",
       "   2.3436418,\n",
       "   2.3471045,\n",
       "   2.2744477,\n",
       "   2.245617,\n",
       "   2.216309,\n",
       "   2.2329648,\n",
       "   2.1841388,\n",
       "   2.1780539,\n",
       "   2.1625984,\n",
       "   2.2195568,\n",
       "   2.1803434,\n",
       "   2.1858895,\n",
       "   2.1908271,\n",
       "   2.1841395,\n",
       "   2.1843896,\n",
       "   2.154806,\n",
       "   2.1130056,\n",
       "   2.113019,\n",
       "   2.1191697,\n",
       "   2.1213412,\n",
       "   2.1077166,\n",
       "   2.0737479,\n",
       "   2.07655,\n",
       "   2.0769904,\n",
       "   2.061769,\n",
       "   2.0676718,\n",
       "   2.0859065,\n",
       "   2.0704215,\n",
       "   2.1113508,\n",
       "   2.0382714,\n",
       "   2.0911386,\n",
       "   2.0458508,\n",
       "   2.0786576,\n",
       "   2.026332,\n",
       "   2.0141299,\n",
       "   2.0226884,\n",
       "   2.0182638,\n",
       "   2.0110855,\n",
       "   2.0191038,\n",
       "   2.0334535,\n",
       "   2.0072439,\n",
       "   2.0296187,\n",
       "   1.9912667,\n",
       "   2.006095,\n",
       "   2.012164,\n",
       "   1.9955354,\n",
       "   2.005768,\n",
       "   2.015392,\n",
       "   1.9890119,\n",
       "   2.0090258,\n",
       "   1.9728817,\n",
       "   1.9769167,\n",
       "   1.9980135,\n",
       "   1.9884782,\n",
       "   1.9772192,\n",
       "   1.9732709,\n",
       "   1.9623082,\n",
       "   1.9812362,\n",
       "   1.9846246,\n",
       "   1.9822198,\n",
       "   1.9768158,\n",
       "   1.9625885,\n",
       "   1.9738724,\n",
       "   1.9842362,\n",
       "   1.9709526,\n",
       "   1.967775,\n",
       "   1.9626708,\n",
       "   1.96621,\n",
       "   1.9742922,\n",
       "   1.9604725,\n",
       "   1.9733659,\n",
       "   1.9693874,\n",
       "   1.9647765,\n",
       "   1.9649359]},\n",
       " 'VGG_38': {'train_acc': [0.009263157894736843,\n",
       "   0.009810526315789474,\n",
       "   0.009705263157894738,\n",
       "   0.008989473684210525,\n",
       "   0.009747368421052633,\n",
       "   0.00951578947368421,\n",
       "   0.009789473684210525,\n",
       "   0.009936842105263159,\n",
       "   0.009810526315789474,\n",
       "   0.009094736842105263,\n",
       "   0.008421052631578947,\n",
       "   0.009010526315789472,\n",
       "   0.009894736842105263,\n",
       "   0.00934736842105263,\n",
       "   0.009473684210526316,\n",
       "   0.010252631578947369,\n",
       "   0.009536842105263158,\n",
       "   0.00848421052631579,\n",
       "   0.008421052631578947,\n",
       "   0.009410526315789473,\n",
       "   0.009263157894736843,\n",
       "   0.009389473684210526,\n",
       "   0.008989473684210528,\n",
       "   0.009326315789473686,\n",
       "   0.01,\n",
       "   0.008778947368421053,\n",
       "   0.009326315789473684,\n",
       "   0.009031578947368422,\n",
       "   0.008842105263157896,\n",
       "   0.008968421052631579,\n",
       "   0.008947368421052631,\n",
       "   0.008842105263157896,\n",
       "   0.008799999999999999,\n",
       "   0.009326315789473686,\n",
       "   0.00905263157894737,\n",
       "   0.00934736842105263,\n",
       "   0.009221052631578948,\n",
       "   0.009557894736842105,\n",
       "   0.009073684210526317,\n",
       "   0.009242105263157895,\n",
       "   0.009957894736842107,\n",
       "   0.009052631578947368,\n",
       "   0.008694736842105264,\n",
       "   0.009536842105263158,\n",
       "   0.009663157894736842,\n",
       "   0.008821052631578948,\n",
       "   0.009768421052631579,\n",
       "   0.0092,\n",
       "   0.008926315789473685,\n",
       "   0.008989473684210525,\n",
       "   0.009242105263157895,\n",
       "   0.009094736842105263,\n",
       "   0.009473684210526316,\n",
       "   0.009494736842105262,\n",
       "   0.009747368421052631,\n",
       "   0.009789473684210527,\n",
       "   0.009199999999999998,\n",
       "   0.009073684210526317,\n",
       "   0.008821052631578948,\n",
       "   0.009326315789473684,\n",
       "   0.009557894736842105,\n",
       "   0.009600000000000001,\n",
       "   0.00856842105263158,\n",
       "   0.009894736842105263,\n",
       "   0.009494736842105262,\n",
       "   0.008673684210526314,\n",
       "   0.009221052631578948,\n",
       "   0.008989473684210528,\n",
       "   0.00928421052631579,\n",
       "   0.0092,\n",
       "   0.008989473684210525,\n",
       "   0.009515789473684212,\n",
       "   0.009073684210526317,\n",
       "   0.009642105263157895,\n",
       "   0.009747368421052633,\n",
       "   0.009873684210526316,\n",
       "   0.009536842105263156,\n",
       "   0.009515789473684212,\n",
       "   0.009978947368421053,\n",
       "   0.009957894736842107,\n",
       "   0.009410526315789475,\n",
       "   0.01002105263157895,\n",
       "   0.01002105263157895,\n",
       "   0.00951578947368421,\n",
       "   0.009852631578947368,\n",
       "   0.009894736842105265,\n",
       "   0.00922105263157895,\n",
       "   0.010042105263157896,\n",
       "   0.009978947368421053,\n",
       "   0.009747368421052633,\n",
       "   0.010189473684210526,\n",
       "   0.009789473684210527,\n",
       "   0.009936842105263159,\n",
       "   0.010042105263157894,\n",
       "   0.009494736842105262,\n",
       "   0.009536842105263158,\n",
       "   0.010021052631578946,\n",
       "   0.009747368421052631,\n",
       "   0.009642105263157895,\n",
       "   0.009305263157894737],\n",
       "  'train_loss': [4.8649125,\n",
       "   4.6264124,\n",
       "   4.621914,\n",
       "   4.619472,\n",
       "   4.6168556,\n",
       "   4.6156826,\n",
       "   4.614809,\n",
       "   4.613147,\n",
       "   4.612325,\n",
       "   4.6117926,\n",
       "   4.611283,\n",
       "   4.6105323,\n",
       "   4.6103206,\n",
       "   4.6095214,\n",
       "   4.6095295,\n",
       "   4.609189,\n",
       "   4.6087623,\n",
       "   4.6086617,\n",
       "   4.6083455,\n",
       "   4.608145,\n",
       "   4.6078997,\n",
       "   4.607453,\n",
       "   4.6075597,\n",
       "   4.607266,\n",
       "   4.607154,\n",
       "   4.607089,\n",
       "   4.606807,\n",
       "   4.6068263,\n",
       "   4.6066294,\n",
       "   4.606647,\n",
       "   4.6065364,\n",
       "   4.6064167,\n",
       "   4.606425,\n",
       "   4.606305,\n",
       "   4.606274,\n",
       "   4.6062336,\n",
       "   4.606221,\n",
       "   4.60607,\n",
       "   4.6061006,\n",
       "   4.606005,\n",
       "   4.605986,\n",
       "   4.605935,\n",
       "   4.6059127,\n",
       "   4.605874,\n",
       "   4.605872,\n",
       "   4.6057997,\n",
       "   4.605778,\n",
       "   4.6057644,\n",
       "   4.6057386,\n",
       "   4.6057277,\n",
       "   4.6057053,\n",
       "   4.605692,\n",
       "   4.60566,\n",
       "   4.605613,\n",
       "   4.6056285,\n",
       "   4.605578,\n",
       "   4.6055675,\n",
       "   4.6055593,\n",
       "   4.6055293,\n",
       "   4.6055255,\n",
       "   4.6055083,\n",
       "   4.605491,\n",
       "   4.605466,\n",
       "   4.605463,\n",
       "   4.605441,\n",
       "   4.6054277,\n",
       "   4.6054296,\n",
       "   4.605404,\n",
       "   4.6053905,\n",
       "   4.6053743,\n",
       "   4.605368,\n",
       "   4.605355,\n",
       "   4.605352,\n",
       "   4.6053243,\n",
       "   4.6053176,\n",
       "   4.6053023,\n",
       "   4.605297,\n",
       "   4.6052866,\n",
       "   4.605265,\n",
       "   4.605259,\n",
       "   4.6052504,\n",
       "   4.6052403,\n",
       "   4.6052313,\n",
       "   4.605224,\n",
       "   4.605219,\n",
       "   4.605209,\n",
       "   4.605204,\n",
       "   4.605193,\n",
       "   4.6051874,\n",
       "   4.605183,\n",
       "   4.605178,\n",
       "   4.605173,\n",
       "   4.605169,\n",
       "   4.605166,\n",
       "   4.6051593,\n",
       "   4.6051593,\n",
       "   4.6051564,\n",
       "   4.605154,\n",
       "   4.605153,\n",
       "   4.6051517],\n",
       "  'val_acc': [0.0104,\n",
       "   0.009600000000000001,\n",
       "   0.011200000000000002,\n",
       "   0.0064,\n",
       "   0.0076,\n",
       "   0.0108,\n",
       "   0.008400000000000001,\n",
       "   0.0104,\n",
       "   0.0076,\n",
       "   0.007200000000000001,\n",
       "   0.011600000000000001,\n",
       "   0.009600000000000001,\n",
       "   0.008400000000000001,\n",
       "   0.011200000000000002,\n",
       "   0.008,\n",
       "   0.0104,\n",
       "   0.0092,\n",
       "   0.009600000000000001,\n",
       "   0.011200000000000002,\n",
       "   0.0068000000000000005,\n",
       "   0.0092,\n",
       "   0.01,\n",
       "   0.008400000000000001,\n",
       "   0.008,\n",
       "   0.0076,\n",
       "   0.011200000000000002,\n",
       "   0.0068,\n",
       "   0.011200000000000002,\n",
       "   0.008,\n",
       "   0.006400000000000001,\n",
       "   0.0092,\n",
       "   0.0076,\n",
       "   0.0096,\n",
       "   0.0072,\n",
       "   0.0072,\n",
       "   0.007200000000000001,\n",
       "   0.0076,\n",
       "   0.0076,\n",
       "   0.0072,\n",
       "   0.0064,\n",
       "   0.0072,\n",
       "   0.0072,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0072,\n",
       "   0.0064,\n",
       "   0.0072,\n",
       "   0.007200000000000001,\n",
       "   0.0072,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0063999999999999994,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0063999999999999994,\n",
       "   0.006400000000000001,\n",
       "   0.0064,\n",
       "   0.0064,\n",
       "   0.0064],\n",
       "  'val_loss': [4.630689,\n",
       "   4.618983,\n",
       "   4.6184525,\n",
       "   4.6164784,\n",
       "   4.6138463,\n",
       "   4.6139345,\n",
       "   4.6116896,\n",
       "   4.6148276,\n",
       "   4.6123877,\n",
       "   4.6149993,\n",
       "   4.6114736,\n",
       "   4.607559,\n",
       "   4.6086206,\n",
       "   4.6091933,\n",
       "   4.6095695,\n",
       "   4.610459,\n",
       "   4.6091356,\n",
       "   4.609126,\n",
       "   4.6088147,\n",
       "   4.608519,\n",
       "   4.6085033,\n",
       "   4.6083508,\n",
       "   4.6073136,\n",
       "   4.6069093,\n",
       "   4.6069508,\n",
       "   4.60659,\n",
       "   4.6072598,\n",
       "   4.607257,\n",
       "   4.606883,\n",
       "   4.607275,\n",
       "   4.606976,\n",
       "   4.607016,\n",
       "   4.607184,\n",
       "   4.6068683,\n",
       "   4.606982,\n",
       "   4.607209,\n",
       "   4.607369,\n",
       "   4.6074376,\n",
       "   4.607068,\n",
       "   4.6067224,\n",
       "   4.6068263,\n",
       "   4.6067867,\n",
       "   4.6070905,\n",
       "   4.606976,\n",
       "   4.6068897,\n",
       "   4.607028,\n",
       "   4.6069264,\n",
       "   4.607018,\n",
       "   4.60698,\n",
       "   4.6070237,\n",
       "   4.6069183,\n",
       "   4.6068764,\n",
       "   4.606909,\n",
       "   4.606978,\n",
       "   4.606753,\n",
       "   4.6068797,\n",
       "   4.606888,\n",
       "   4.606874,\n",
       "   4.606851,\n",
       "   4.606871,\n",
       "   4.606851,\n",
       "   4.6068635,\n",
       "   4.606862,\n",
       "   4.6068873,\n",
       "   4.6068926,\n",
       "   4.6068554,\n",
       "   4.6068907,\n",
       "   4.6068807,\n",
       "   4.6068707,\n",
       "   4.606894,\n",
       "   4.606845,\n",
       "   4.6068635,\n",
       "   4.6068773,\n",
       "   4.606883,\n",
       "   4.6069,\n",
       "   4.6068873,\n",
       "   4.6068654,\n",
       "   4.6068883,\n",
       "   4.606894,\n",
       "   4.6068826,\n",
       "   4.6068697,\n",
       "   4.6068807,\n",
       "   4.606872,\n",
       "   4.6068883,\n",
       "   4.606871,\n",
       "   4.606871,\n",
       "   4.6068654,\n",
       "   4.6068764,\n",
       "   4.6068697,\n",
       "   4.6068673,\n",
       "   4.606873,\n",
       "   4.6068773,\n",
       "   4.606874,\n",
       "   4.606877,\n",
       "   4.606874,\n",
       "   4.606874,\n",
       "   4.6068716,\n",
       "   4.6068726,\n",
       "   4.606872,\n",
       "   4.6068726]}}"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_dict"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}