{
  "id": 459865,
  "title": "79th Place Solution. 🥈",
  "url": "/competitions/child-mind-institute-detect-sleep-states/discussion/459865",
  "author_name": "__Taichicchi__",
  "post_date": "2023-12-06T20:48:52.566000",
  "votes": 7,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Dear Kagglers.</p>\n<p>Thank you to the competition organizers hosting this interesting competition.<br>\nThank you to everyone involved in this competition. I learned a lot from public notebooks and discussions.</p>\n<h1>My Final Result</h1>\n<ul>\n<li><p>Score<br>\nPublic: 0.751 → Private 0.786</p></li>\n<li><p>LeaderBoard<br>\nPublic: 52nd → Private 79th 🥈</p></li>\n</ul>\n<h1>Summary of Solution</h1>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F1836c58970cc7d4f7691e8efc8861355%2Fsolution.drawio.png?generation=1701895087837059&amp;alt=media\" alt=\"\"></p>\n<ol>\n<li><p>common settings</p>\n<ul>\n<li>criterion: focal loss</li></ul></li>\n<li><p>1DUnet<br>\nbased on these <a href=\"https://www.kaggle.com/werus23\" target=\"_blank\">@werus23</a>'s and <a href=\"https://www.kaggle.com/danielphalen\" target=\"_blank\">@danielphalen</a>'s notebooks, I modified loss criterion, dataset, features, architecture, etc.</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/code/werus23/sleep-critical-point-train\" target=\"_blank\">https://www.kaggle.com/code/werus23/sleep-critical-point-train</a></li>\n<li><a href=\"https://www.kaggle.com/code/werus23/sleep-critical-point-infer\" target=\"_blank\">https://www.kaggle.com/code/werus23/sleep-critical-point-infer</a></li>\n<li><a href=\"https://www.kaggle.com/code/danielphalen/cmss-grunet-train\" target=\"_blank\">https://www.kaggle.com/code/danielphalen/cmss-grunet-train</a></li>\n<li><a href=\"https://www.kaggle.com/code/danielphalen/cmss-grunet-infer\" target=\"_blank\">https://www.kaggle.com/code/danielphalen/cmss-grunet-infer</a></li></ul>\n<p>architecture<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F73f3fbff32b9c5b76a2c2f88377c7bed%2F1dunet.drawio.png?generation=1701893136038754&amp;alt=media\" alt=\"\"></p></li>\n<li><p>Spec2DCNN<br>\nbased on <a href=\"https://www.kaggle.com/tubotubo\" target=\"_blank\">@tubotubo</a>'s public repository, I added focal loss criterion.</p>\n<ul>\n<li><a href=\"https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states\" target=\"_blank\">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states</a></li>\n<li><a href=\"https://www.kaggle.com/code/tubotubo/cmi-submit\" target=\"_blank\">https://www.kaggle.com/code/tubotubo/cmi-submit</a></li></ul></li>\n</ol>\n<h1>Source (inference notebook)</h1>\n<p><a href=\"https://www.kaggle.com/code/hutch1221/cmi-ensemble\" target=\"_blank\">https://www.kaggle.com/code/hutch1221/cmi-ensemble</a></p>\n<h1>Finally</h1>\n<p>I gained significant insights into event detection techniques from the public notebooks and discussions. In particular, the public codes shared by <a href=\"https://www.kaggle.com/werus23\" target=\"_blank\">@werus23</a>, <a href=\"https://www.kaggle.com/danielphalen\" target=\"_blank\">@danielphalen</a>, and <a href=\"https://www.kaggle.com/tubotubo\" target=\"_blank\">@tubotubo</a> were outstanding and contributed greatly to my learning.</p>\n<p>Advice is always welcome!<br>\nThank you for your attention.</p>",
  "messages": [
    {
      "id": 2551636,
      "postDate": "2023-12-06T20:48:52.567Z",
      "content": "<p>Dear Kagglers.</p>\n<p>Thank you to the competition organizers hosting this interesting competition.<br>\nThank you to everyone involved in this competition. I learned a lot from public notebooks and discussions.</p>\n<h1>My Final Result</h1>\n<ul>\n<li><p>Score<br>\nPublic: 0.751 → Private 0.786</p></li>\n<li><p>LeaderBoard<br>\nPublic: 52nd → Private 79th 🥈</p></li>\n</ul>\n<h1>Summary of Solution</h1>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F1836c58970cc7d4f7691e8efc8861355%2Fsolution.drawio.png?generation=1701895087837059&amp;alt=media\" alt=\"\"></p>\n<ol>\n<li><p>common settings</p>\n<ul>\n<li>criterion: focal loss</li></ul></li>\n<li><p>1DUnet<br>\nbased on these <a href=\"https://www.kaggle.com/werus23\" target=\"_blank\">@werus23</a>'s and <a href=\"https://www.kaggle.com/danielphalen\" target=\"_blank\">@danielphalen</a>'s notebooks, I modified loss criterion, dataset, features, architecture, etc.</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/code/werus23/sleep-critical-point-train\" target=\"_blank\">https://www.kaggle.com/code/werus23/sleep-critical-point-train</a></li>\n<li><a href=\"https://www.kaggle.com/code/werus23/sleep-critical-point-infer\" target=\"_blank\">https://www.kaggle.com/code/werus23/sleep-critical-point-infer</a></li>\n<li><a href=\"https://www.kaggle.com/code/danielphalen/cmss-grunet-train\" target=\"_blank\">https://www.kaggle.com/code/danielphalen/cmss-grunet-train</a></li>\n<li><a href=\"https://www.kaggle.com/code/danielphalen/cmss-grunet-infer\" target=\"_blank\">https://www.kaggle.com/code/danielphalen/cmss-grunet-infer</a></li></ul>\n<p>architecture<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F73f3fbff32b9c5b76a2c2f88377c7bed%2F1dunet.drawio.png?generation=1701893136038754&amp;alt=media\" alt=\"\"></p></li>\n<li><p>Spec2DCNN<br>\nbased on <a href=\"https://www.kaggle.com/tubotubo\" target=\"_blank\">@tubotubo</a>'s public repository, I added focal loss criterion.</p>\n<ul>\n<li><a href=\"https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states\" target=\"_blank\">https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states</a></li>\n<li><a href=\"https://www.kaggle.com/code/tubotubo/cmi-submit\" target=\"_blank\">https://www.kaggle.com/code/tubotubo/cmi-submit</a></li></ul></li>\n</ol>\n<h1>Source (inference notebook)</h1>\n<p><a href=\"https://www.kaggle.com/code/hutch1221/cmi-ensemble\" target=\"_blank\">https://www.kaggle.com/code/hutch1221/cmi-ensemble</a></p>\n<h1>Finally</h1>\n<p>I gained significant insights into event detection techniques from the public notebooks and discussions. In particular, the public codes shared by <a href=\"https://www.kaggle.com/werus23\" target=\"_blank\">@werus23</a>, <a href=\"https://www.kaggle.com/danielphalen\" target=\"_blank\">@danielphalen</a>, and <a href=\"https://www.kaggle.com/tubotubo\" target=\"_blank\">@tubotubo</a> were outstanding and contributed greatly to my learning.</p>\n<p>Advice is always welcome!<br>\nThank you for your attention.</p>",
      "rawMarkdown": "Dear Kagglers.\n\nThank you to the competition organizers hosting this interesting competition.\nThank you to everyone involved in this competition. I learned a lot from public notebooks and discussions.\n\n\n# My Final Result\n\n- Score\nPublic: 0.751 → Private 0.786\n\n- LeaderBoard\nPublic: 52nd → Private 79th 🥈\n\n\n\n# Summary of Solution\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F1836c58970cc7d4f7691e8efc8861355%2Fsolution.drawio.png?generation=1701895087837059&alt=media)\n\n\n0. common settings\n   - criterion: focal loss\n\n\n1. 1DUnet\n   based on these @werus23's and @danielphalen's notebooks, I modified loss criterion, dataset, features, architecture, etc.\n   - https://www.kaggle.com/code/werus23/sleep-critical-point-train\n   - https://www.kaggle.com/code/werus23/sleep-critical-point-infer\n   - https://www.kaggle.com/code/danielphalen/cmss-grunet-train\n   - https://www.kaggle.com/code/danielphalen/cmss-grunet-infer\n\n    architecture\n    ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F73f3fbff32b9c5b76a2c2f88377c7bed%2F1dunet.drawio.png?generation=1701893136038754&alt=media)\n    \n\n2. Spec2DCNN\n   based on @tubotubo's public repository, I added focal loss criterion.\n   - https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states\n   - https://www.kaggle.com/code/tubotubo/cmi-submit\n\n# Source (inference notebook)\nhttps://www.kaggle.com/code/hutch1221/cmi-ensemble\n\n# Finally\nI gained significant insights into event detection techniques from the public notebooks and discussions. In particular, the public codes shared by @werus23, @danielphalen, and @tubotubo were outstanding and contributed greatly to my learning.\n\nAdvice is always welcome!\nThank you for your attention.\n",
      "votes": 7
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2551636": "Dear Kagglers.\n\nThank you to the competition organizers hosting this interesting competition.\nThank you to everyone involved in this competition. I learned a lot from public notebooks and discussions.\n\n\n# My Final Result\n\n- Score\nPublic: 0.751 → Private 0.786\n\n- LeaderBoard\nPublic: 52nd → Private 79th 🥈\n\n\n\n# Summary of Solution\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F1836c58970cc7d4f7691e8efc8861355%2Fsolution.drawio.png?generation=1701895087837059&alt=media)\n\n\n0. common settings\n   - criterion: focal loss\n\n\n1. 1DUnet\n   based on these @werus23's and @danielphalen's notebooks, I modified loss criterion, dataset, features, architecture, etc.\n   - https://www.kaggle.com/code/werus23/sleep-critical-point-train\n   - https://www.kaggle.com/code/werus23/sleep-critical-point-infer\n   - https://www.kaggle.com/code/danielphalen/cmss-grunet-train\n   - https://www.kaggle.com/code/danielphalen/cmss-grunet-infer\n\n    architecture\n    ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1452109%2F73f3fbff32b9c5b76a2c2f88377c7bed%2F1dunet.drawio.png?generation=1701893136038754&alt=media)\n    \n\n2. Spec2DCNN\n   based on @tubotubo's public repository, I added focal loss criterion.\n   - https://github.com/tubo213/kaggle-child-mind-institute-detect-sleep-states\n   - https://www.kaggle.com/code/tubotubo/cmi-submit\n\n# Source (inference notebook)\nhttps://www.kaggle.com/code/hutch1221/cmi-ensemble\n\n# Finally\nI gained significant insights into event detection techniques from the public notebooks and discussions. In particular, the public codes shared by @werus23, @danielphalen, and @tubotubo were outstanding and contributed greatly to my learning.\n\nAdvice is always welcome!\nThank you for your attention.\n"
  },
  "complete": true,
  "source": "existing_discussion",
  "competition_id": 53666,
  "competition_slug": "child-mind-institute-detect-sleep-states",
  "team_id": 11026800,
  "solution_url": "/competitions/child-mind-institute-detect-sleep-states/writeups/taichicchi-79th-place-solution"
}