{
  "id": 250471,
  "title": "I hope this helps someone - SR 2048 : New dataset",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/250471",
  "author_name": "",
  "post_date": "2021-07-02T20:45:57.162890Z",
  "votes": 12,
  "comment_count": 1,
  "views": 0,
  "content": "<blockquote>\n  <p>Each data sample (npy file) contains 3 time series (1 for each detector) and each spans 2 sec and is sampled at 2,048 Hz.</p>\n</blockquote>\n<p>The dataset I shared below is sr=2048. It seems that it would be better to also change <code>fmax</code> to <code>1024</code>.</p>\n<ul>\n<li><p><code>sr=2048</code> (<code>version1</code>)<br>\n<img src=\"https://imgur.com/rIcOH4S.jpg\" alt=\"\"></p></li>\n<li><p><code>sr=2048</code> &amp; <code>fmax=1024</code> (<code>version2</code>)<br>\n<img src=\"https://imgur.com/xBd9mkF.jpg\" alt=\"\"></p></li>\n</ul>\n<p>The link below has both <code>version1</code> and <code>version2</code>.</p>\n<ul>\n<li> (After 20 min, the dataset will be updated to <code>version2</code>.) updated has been failed. please use train dataset in generation code.</li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-spectrogram-generation-train-sr-2048?scriptVersionId=67278253\" target=\"_blank\">train dataset generation code for sr=2048</a><br>\n<br></li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-test-images\" target=\"_blank\">test dataset link for sr=2048</a> </li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-spectrogram-generation-test-sr-2048\" target=\"_blank\">test dataset generation code for sr=2048</a></li>\n</ul>\n<p>p.s. I used the <a href=\"https://www.kaggle.com/Y.Nakama\" target=\"_blank\">@Y.Nakama</a>'s original notebook.</p>\n<p>Thank you!</p>",
  "messages": [
    {
      "id": "1373933",
      "postDate": "07/02/2021 20:45:57",
      "content": "<blockquote>\n  <p>Each data sample (npy file) contains 3 time series (1 for each detector) and each spans 2 sec and is sampled at 2,048 Hz.</p>\n</blockquote>\n<p>The dataset I shared below is sr=2048. It seems that it would be better to also change <code>fmax</code> to <code>1024</code>.</p>\n<ul>\n<li><p><code>sr=2048</code> (<code>version1</code>)<br>\n<img src=\"https://imgur.com/rIcOH4S.jpg\" alt=\"\"></p></li>\n<li><p><code>sr=2048</code> &amp; <code>fmax=1024</code> (<code>version2</code>)<br>\n<img src=\"https://imgur.com/xBd9mkF.jpg\" alt=\"\"></p></li>\n</ul>\n<p>The link below has both <code>version1</code> and <code>version2</code>.</p>\n<ul>\n<li> (After 20 min, the dataset will be updated to <code>version2</code>.) updated has been failed. please use train dataset in generation code.</li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-spectrogram-generation-train-sr-2048?scriptVersionId=67278253\" target=\"_blank\">train dataset generation code for sr=2048</a><br>\n<br></li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-test-images\" target=\"_blank\">test dataset link for sr=2048</a> </li>\n<li><a href=\"https://www.kaggle.com/piantic/g2net-spectrogram-generation-test-sr-2048\" target=\"_blank\">test dataset generation code for sr=2048</a></li>\n</ul>\n<p>p.s. I used the <a href=\"https://www.kaggle.com/Y.Nakama\" target=\"_blank\">@Y.Nakama</a>'s original notebook.</p>\n<p>Thank you!</p>",
      "rawMarkdown": "> Each data sample (npy file) contains 3 time series (1 for each detector) and each spans 2 sec and is sampled at 2,048 Hz.\n\nThe dataset I shared below is sr=2048. It seems that it would be better to also change `fmax` to `1024`.\n\n- `sr=2048` (`version1`)\n![](https://imgur.com/rIcOH4S.jpg)\n\n- `sr=2048` & `fmax=1024` (`version2`)\n![](https://imgur.com/xBd9mkF.jpg)\n\n\n\nThe link below has both `version1` and `version2`.\n\n\n- ~~[train dataset link for sr=2048](https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-train-images)~~ (After 20 min, the dataset will be updated to `version2`.) updated has been failed. please use train dataset in generation code.\n-  [train dataset generation code for sr=2048](https://www.kaggle.com/piantic/g2net-spectrogram-generation-train-sr-2048?scriptVersionId=67278253)\n</br>\n- [test dataset link for sr=2048](https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-test-images) \n- [test dataset generation code for sr=2048](https://www.kaggle.com/piantic/g2net-spectrogram-generation-test-sr-2048)\n\np.s. I used the @Y.Nakama's original notebook.\n\nThank you!",
      "votes": null
    },
    {
      "id": "1563250",
      "postDate": "10/28/2021 06:51:35",
      "content": "<p>Hey,</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,\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": 1563250,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/28/2021 06:51:35",
      "content": "<p>Hey,</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": {
    "1373933": "> Each data sample (npy file) contains 3 time series (1 for each detector) and each spans 2 sec and is sampled at 2,048 Hz.\n\nThe dataset I shared below is sr=2048. It seems that it would be better to also change `fmax` to `1024`.\n\n- `sr=2048` (`version1`)\n![](https://imgur.com/rIcOH4S.jpg)\n\n- `sr=2048` & `fmax=1024` (`version2`)\n![](https://imgur.com/xBd9mkF.jpg)\n\n\n\nThe link below has both `version1` and `version2`.\n\n\n- ~~[train dataset link for sr=2048](https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-train-images)~~ (After 20 min, the dataset will be updated to `version2`.) updated has been failed. please use train dataset in generation code.\n-  [train dataset generation code for sr=2048](https://www.kaggle.com/piantic/g2net-spectrogram-generation-train-sr-2048?scriptVersionId=67278253)\n</br>\n- [test dataset link for sr=2048](https://www.kaggle.com/piantic/g2net-n-mels-128-sr-2048-test-images) \n- [test dataset generation code for sr=2048](https://www.kaggle.com/piantic/g2net-spectrogram-generation-test-sr-2048)\n\np.s. I used the @Y.Nakama's original notebook.\n\nThank you!",
    "1563250": "Hey,\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"
}