{
  "id": 270133,
  "title": "How to weave together fastai, the timm library and nnAudio",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/270133",
  "author_name": "",
  "post_date": "2021-09-03T17:36:57.646686700Z",
  "votes": 4,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I have made a <a href=\"https://www.kaggle.com/sapal6/g2gwd-basemodel-nnaudio-timm-fastai?rvi=1\" target=\"_blank\">notebook</a> where I have shown how to use fastai with timm library and nnAudio. </p>\n<p>Some of the advantage being-</p>\n<ol>\n<li>Flexible API to play around.</li>\n<li>Some out of the box goodies like Learning rate finder and discriminative learning rate.</li>\n<li>Show methods to quickly visualize and debug.</li>\n</ol>\n<p>I wanted to experiment about how to join together these different libraries together and this is the first iteration to do so. I hope that this would be of help to someone who is trying to do the same.</p>",
  "messages": [
    {
      "id": "1501981",
      "postDate": "09/03/2021 17:36:57",
      "content": "<p>I have made a <a href=\"https://www.kaggle.com/sapal6/g2gwd-basemodel-nnaudio-timm-fastai?rvi=1\" target=\"_blank\">notebook</a> where I have shown how to use fastai with timm library and nnAudio. </p>\n<p>Some of the advantage being-</p>\n<ol>\n<li>Flexible API to play around.</li>\n<li>Some out of the box goodies like Learning rate finder and discriminative learning rate.</li>\n<li>Show methods to quickly visualize and debug.</li>\n</ol>\n<p>I wanted to experiment about how to join together these different libraries together and this is the first iteration to do so. I hope that this would be of help to someone who is trying to do the same.</p>",
      "rawMarkdown": "I have made a [notebook](https://www.kaggle.com/sapal6/g2gwd-basemodel-nnaudio-timm-fastai?rvi=1) where I have shown how to use fastai with timm library and nnAudio. \n\nSome of the advantage being-\n\n1. Flexible API to play around.\n2. Some out of the box goodies like Learning rate finder and discriminative learning rate.\n3. Show methods to quickly visualize and debug.\n\nI wanted to experiment about how to join together these different libraries together and this is the first iteration to do so. I hope that this would be of help to someone who is trying to do the same.",
      "votes": null
    },
    {
      "id": "1559954",
      "postDate": "10/27/2021 08:37:06",
      "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": 1559954,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 08:37:06",
      "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": {
    "1501981": "I have made a [notebook](https://www.kaggle.com/sapal6/g2gwd-basemodel-nnaudio-timm-fastai?rvi=1) where I have shown how to use fastai with timm library and nnAudio. \n\nSome of the advantage being-\n\n1. Flexible API to play around.\n2. Some out of the box goodies like Learning rate finder and discriminative learning rate.\n3. Show methods to quickly visualize and debug.\n\nI wanted to experiment about how to join together these different libraries together and this is the first iteration to do so. I hope that this would be of help to someone who is trying to do the same.",
    "1559954": "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"
}