{
  "id": 250517,
  "title": "Preprocessed Dataset",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/250517",
  "author_name": "",
  "post_date": "2021-07-03T06:15:21.347651200Z",
  "votes": 12,
  "comment_count": 5,
  "views": 0,
  "content": "<p>A more effective way for training deep neural networks in this competition is to create the preprocessed dataset and in my mind, some of us will be used the same preprocessed technique or some of us are lazy for preprocessing big data. So let's share and structure preprocessed datasets on this discussion. </p>\n<p>Recommendation:</p>\n<ul>\n<li>describe how are you preprocessed data</li>\n<li>describe dataset data format</li>\n<li>describe how serialize / deserialize dataset</li>\n</ul>",
  "messages": [
    {
      "id": "1374225",
      "postDate": "07/03/2021 06:15:21",
      "content": "<p>A more effective way for training deep neural networks in this competition is to create the preprocessed dataset and in my mind, some of us will be used the same preprocessed technique or some of us are lazy for preprocessing big data. So let's share and structure preprocessed datasets on this discussion. </p>\n<p>Recommendation:</p>\n<ul>\n<li>describe how are you preprocessed data</li>\n<li>describe dataset data format</li>\n<li>describe how serialize / deserialize dataset</li>\n</ul>",
      "rawMarkdown": "A more effective way for training deep neural networks in this competition is to create the preprocessed dataset and in my mind, some of us will be used the same preprocessed technique or some of us are lazy for preprocessing big data. So let's share and structure preprocessed datasets on this discussion. \n\nRecommendation:\n- describe how are you preprocessed data\n- describe dataset data format\n- describe how serialize / deserialize dataset",
      "votes": null
    },
    {
      "id": "1374236",
      "postDate": "07/03/2021 06:27:20",
      "content": "<p>Log Power of Spector with Global MinMax normalization</p>\n<p>Dataset Format: <strong>.tfrecords</strong></p>\n<p>Train Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-03\" target=\"_blank\">G2Net [0-3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-47\" target=\"_blank\">G2Net [4-7]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-812\" target=\"_blank\">G2Net [8-12]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-1215\" target=\"_blank\">G2Net [12-15]</a></li>\n</ul>\n<p>How Train Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/spector-power-tfrecords\" target=\"_blank\">Spector Power(TFRecords)</a></li>\n</ul>\n<p>How to use Train Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-training-cv-0-821\" target=\"_blank\">G2Net EfficientNetB1[TPU Training]</a></li>\n</ul>\n<p>Test Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-03\" target=\"_blank\">G2Net Test [0-3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-47\" target=\"_blank\">G2Net Test [4-7]</a></li>\n</ul>\n<p>How Test Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-0-3\" target=\"_blank\">G2Net Test 0-3</a></li>\n</ul>\n<p>How to use Test Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-evaluate\" target=\"_blank\">G2Net EfficientNetB1[TPU Evaluate]</a></li>\n</ul>",
      "rawMarkdown": "Log Power of Spector with Global MinMax normalization\n\nDataset Format: **.tfrecords**\n\nTrain Datasets\n- [G2Net [0-3]](https://www.kaggle.com/miklgr500/g2net-03)\n- [G2Net [4-7]](https://www.kaggle.com/miklgr500/g2net-47)\n- [G2Net [8-12]](https://www.kaggle.com/miklgr500/g2net-812)\n- [G2Net [12-15]](https://www.kaggle.com/miklgr500/g2net-1215)\n\n\nHow Train Dataset formed:\n- [Spector Power(TFRecords)](https://www.kaggle.com/miklgr500/spector-power-tfrecords)\n\nHow to use Train Dataset:\n- [G2Net EfficientNetB1[TPU Training]](https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-training-cv-0-821)\n\n\nTest Datasets\n- [G2Net Test [0-3]](https://www.kaggle.com/miklgr500/g2net-test-03)\n- [G2Net Test [4-7]](https://www.kaggle.com/miklgr500/g2net-test-47)\n\nHow Test Dataset formed:\n- [G2Net Test 0-3](https://www.kaggle.com/miklgr500/g2net-test-0-3)\n\nHow to use Test Dataset:\n- [G2Net EfficientNetB1[TPU Evaluate]](https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-evaluate)",
      "votes": null
    },
    {
      "id": "1376434",
      "postDate": "07/05/2021 06:24:18",
      "content": "<p>PyCBC Q-Transform with whiten &amp; local min/max normalization</p>\n<p>Dataset Format: <strong>.tfrecords</strong></p>\n<p>Train Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-0-1\" target=\"_blank\">CQT G2Net V2 [0 - 1]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-2-3\" target=\"_blank\">CQT G2Net V2 [2 - 3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-4-5\" target=\"_blank\">CQT G2Net V2 [4 - 5]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-6-7\" target=\"_blank\">CQT G2Net V2 [6 - 7]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-8-9\" target=\"_blank\">CQT G2Net V2 [8 - 9]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-10-11\" target=\"_blank\">CQT G2Net V2 [10 - 11]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-12-13\" target=\"_blank\">CQT G2Net V2 [12 - 13]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-14-15\" target=\"_blank\">CQT G2Net V2 [14 - 15]</a></li>\n</ul>\n<p>How Train Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/q-transform-tfrecords\" target=\"_blank\">Q-Transform TFRecords</a></li>\n</ul>\n<p>How to use Train Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training\" target=\"_blank\">CQT G2Net EfficientNetB1[TPU Training] </a></li>\n</ul>\n<p>Test Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-0-1\" target=\"_blank\">CQT G2Net Test [0 - 1]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-2-3\" target=\"_blank\">CQT G2Net Test [2 - 3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-4-5\" target=\"_blank\">CQT G2Net Test [4 - 5]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-6-7\" target=\"_blank\">CQT G2Net Test [6 - 7]</a></li>\n</ul>\n<p>How Test Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/q-transform-tfrecords-test-0-1\" target=\"_blank\">Q-Transform TFRecords Test 0-1</a></li>\n</ul>\n<p>How to use Test Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training\" target=\"_blank\">CQT G2Net EfficientNetB1[TPU Training] </a></li>\n</ul>",
      "rawMarkdown": "PyCBC Q-Transform with whiten & local min/max normalization\n\nDataset Format: **.tfrecords**\n\nTrain Datasets\n- [CQT G2Net V2 [0 - 1]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-0-1)\n- [CQT G2Net V2 [2 - 3]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-2-3)\n- [CQT G2Net V2 [4 - 5]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-4-5)\n- [CQT G2Net V2 [6 - 7]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-6-7)\n- [CQT G2Net V2 [8 - 9]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-8-9)\n- [CQT G2Net V2 [10 - 11]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-10-11)\n- [CQT G2Net V2 [12 - 13]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-12-13)\n- [CQT G2Net V2 [14 - 15]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-14-15)\n\nHow Train Dataset formed:\n- [Q-Transform TFRecords](https://www.kaggle.com/miklgr500/q-transform-tfrecords)\n\nHow to use Train Dataset:\n- [CQT G2Net EfficientNetB1[TPU Training] ](https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training)\n\nTest Datasets\n- [CQT G2Net Test [0 - 1]](https://www.kaggle.com/miklgr500/cqt-g2net-test-0-1)\n- [CQT G2Net Test [2 - 3]](https://www.kaggle.com/miklgr500/cqt-g2net-test-2-3)\n- [CQT G2Net Test [4 - 5]](https://www.kaggle.com/miklgr500/cqt-g2net-test-4-5)\n- [CQT G2Net Test [6 - 7]](https://www.kaggle.com/miklgr500/cqt-g2net-test-6-7)\n\nHow Test Dataset formed:\n- [Q-Transform TFRecords Test 0-1](https://www.kaggle.com/miklgr500/q-transform-tfrecords-test-0-1)\n\nHow to use Test Dataset:\n- [CQT G2Net EfficientNetB1[TPU Training] ](https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training)",
      "votes": null
    },
    {
      "id": "1396081",
      "postDate": "07/21/2021 18:42:27",
      "content": "<p>Thanks. I haven't done anything yet so this will be a headstart.</p>",
      "rawMarkdown": "Thanks. I haven't done anything yet so this will be a headstart.",
      "votes": null
    },
    {
      "id": "1397566",
      "postDate": "07/23/2021 09:47:00",
      "content": "<p><a href=\"https://www.kaggle.com/miklgr500\" target=\"_blank\">@miklgr500</a> Could you share data in numpy array format !</p>",
      "rawMarkdown": "miklgr500 Could you share data in numpy array format !",
      "votes": null
    },
    {
      "id": "1561277",
      "postDate": "10/27/2021 13:11:48",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1374236,
      "author_name": "miklgr500",
      "author_url": "",
      "post_date": "07/03/2021 06:27:20",
      "content": "<p>Log Power of Spector with Global MinMax normalization</p>\n<p>Dataset Format: <strong>.tfrecords</strong></p>\n<p>Train Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-03\" target=\"_blank\">G2Net [0-3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-47\" target=\"_blank\">G2Net [4-7]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-812\" target=\"_blank\">G2Net [8-12]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-1215\" target=\"_blank\">G2Net [12-15]</a></li>\n</ul>\n<p>How Train Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/spector-power-tfrecords\" target=\"_blank\">Spector Power(TFRecords)</a></li>\n</ul>\n<p>How to use Train Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-training-cv-0-821\" target=\"_blank\">G2Net EfficientNetB1[TPU Training]</a></li>\n</ul>\n<p>Test Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-03\" target=\"_blank\">G2Net Test [0-3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-47\" target=\"_blank\">G2Net Test [4-7]</a></li>\n</ul>\n<p>How Test Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-test-0-3\" target=\"_blank\">G2Net Test 0-3</a></li>\n</ul>\n<p>How to use Test Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-evaluate\" target=\"_blank\">G2Net EfficientNetB1[TPU Evaluate]</a></li>\n</ul>",
      "votes": null,
      "replies": [
        {
          "id": 1397566,
          "author_name": "lhkhiem28",
          "author_url": "",
          "post_date": "07/23/2021 09:47:00",
          "content": "<p><a href=\"https://www.kaggle.com/miklgr500\" target=\"_blank\">@miklgr500</a> Could you share data in numpy array format !</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1376434,
      "author_name": "miklgr500",
      "author_url": "",
      "post_date": "07/05/2021 06:24:18",
      "content": "<p>PyCBC Q-Transform with whiten &amp; local min/max normalization</p>\n<p>Dataset Format: <strong>.tfrecords</strong></p>\n<p>Train Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-0-1\" target=\"_blank\">CQT G2Net V2 [0 - 1]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-2-3\" target=\"_blank\">CQT G2Net V2 [2 - 3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-4-5\" target=\"_blank\">CQT G2Net V2 [4 - 5]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-6-7\" target=\"_blank\">CQT G2Net V2 [6 - 7]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-8-9\" target=\"_blank\">CQT G2Net V2 [8 - 9]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-10-11\" target=\"_blank\">CQT G2Net V2 [10 - 11]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-12-13\" target=\"_blank\">CQT G2Net V2 [12 - 13]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-v2-14-15\" target=\"_blank\">CQT G2Net V2 [14 - 15]</a></li>\n</ul>\n<p>How Train Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/q-transform-tfrecords\" target=\"_blank\">Q-Transform TFRecords</a></li>\n</ul>\n<p>How to use Train Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training\" target=\"_blank\">CQT G2Net EfficientNetB1[TPU Training] </a></li>\n</ul>\n<p>Test Datasets</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-0-1\" target=\"_blank\">CQT G2Net Test [0 - 1]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-2-3\" target=\"_blank\">CQT G2Net Test [2 - 3]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-4-5\" target=\"_blank\">CQT G2Net Test [4 - 5]</a></li>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-test-6-7\" target=\"_blank\">CQT G2Net Test [6 - 7]</a></li>\n</ul>\n<p>How Test Dataset formed:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/q-transform-tfrecords-test-0-1\" target=\"_blank\">Q-Transform TFRecords Test 0-1</a></li>\n</ul>\n<p>How to use Test Dataset:</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training\" target=\"_blank\">CQT G2Net EfficientNetB1[TPU Training] </a></li>\n</ul>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1396081,
      "author_name": "abhishekprajapat",
      "author_url": "",
      "post_date": "07/21/2021 18:42:27",
      "content": "<p>Thanks. I haven't done anything yet so this will be a headstart.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1561277,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 13:11:48",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1374225": "A more effective way for training deep neural networks in this competition is to create the preprocessed dataset and in my mind, some of us will be used the same preprocessed technique or some of us are lazy for preprocessing big data. So let's share and structure preprocessed datasets on this discussion. \n\nRecommendation:\n- describe how are you preprocessed data\n- describe dataset data format\n- describe how serialize / deserialize dataset",
    "1374236": "Log Power of Spector with Global MinMax normalization\n\nDataset Format: **.tfrecords**\n\nTrain Datasets\n- [G2Net [0-3]](https://www.kaggle.com/miklgr500/g2net-03)\n- [G2Net [4-7]](https://www.kaggle.com/miklgr500/g2net-47)\n- [G2Net [8-12]](https://www.kaggle.com/miklgr500/g2net-812)\n- [G2Net [12-15]](https://www.kaggle.com/miklgr500/g2net-1215)\n\n\nHow Train Dataset formed:\n- [Spector Power(TFRecords)](https://www.kaggle.com/miklgr500/spector-power-tfrecords)\n\nHow to use Train Dataset:\n- [G2Net EfficientNetB1[TPU Training]](https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-training-cv-0-821)\n\n\nTest Datasets\n- [G2Net Test [0-3]](https://www.kaggle.com/miklgr500/g2net-test-03)\n- [G2Net Test [4-7]](https://www.kaggle.com/miklgr500/g2net-test-47)\n\nHow Test Dataset formed:\n- [G2Net Test 0-3](https://www.kaggle.com/miklgr500/g2net-test-0-3)\n\nHow to use Test Dataset:\n- [G2Net EfficientNetB1[TPU Evaluate]](https://www.kaggle.com/miklgr500/g2net-efficientnetb1-tpu-evaluate)",
    "1376434": "PyCBC Q-Transform with whiten & local min/max normalization\n\nDataset Format: **.tfrecords**\n\nTrain Datasets\n- [CQT G2Net V2 [0 - 1]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-0-1)\n- [CQT G2Net V2 [2 - 3]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-2-3)\n- [CQT G2Net V2 [4 - 5]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-4-5)\n- [CQT G2Net V2 [6 - 7]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-6-7)\n- [CQT G2Net V2 [8 - 9]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-8-9)\n- [CQT G2Net V2 [10 - 11]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-10-11)\n- [CQT G2Net V2 [12 - 13]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-12-13)\n- [CQT G2Net V2 [14 - 15]](https://www.kaggle.com/miklgr500/cqt-g2net-v2-14-15)\n\nHow Train Dataset formed:\n- [Q-Transform TFRecords](https://www.kaggle.com/miklgr500/q-transform-tfrecords)\n\nHow to use Train Dataset:\n- [CQT G2Net EfficientNetB1[TPU Training] ](https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training)\n\nTest Datasets\n- [CQT G2Net Test [0 - 1]](https://www.kaggle.com/miklgr500/cqt-g2net-test-0-1)\n- [CQT G2Net Test [2 - 3]](https://www.kaggle.com/miklgr500/cqt-g2net-test-2-3)\n- [CQT G2Net Test [4 - 5]](https://www.kaggle.com/miklgr500/cqt-g2net-test-4-5)\n- [CQT G2Net Test [6 - 7]](https://www.kaggle.com/miklgr500/cqt-g2net-test-6-7)\n\nHow Test Dataset formed:\n- [Q-Transform TFRecords Test 0-1](https://www.kaggle.com/miklgr500/q-transform-tfrecords-test-0-1)\n\nHow to use Test Dataset:\n- [CQT G2Net EfficientNetB1[TPU Training] ](https://www.kaggle.com/miklgr500/cqt-g2net-efficientnetb1-tpu-training)",
    "1396081": "Thanks. I haven't done anything yet so this will be a headstart.",
    "1397566": "miklgr500 Could you share data in numpy array format !",
    "1561277": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}