{
  "id": 478474,
  "title": "[LB 0.43] Resnet1D_GRU EEG Only Pytorch",
  "url": "/competitions/hms-harmful-brain-activity-classification/discussion/478474",
  "author_name": "Med Ali Bouchhioua",
  "post_date": "2024-02-20T22:26:26.600000",
  "votes": 16,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hello everyone,</p>\n<p>After reading this forum, [CV 0.68 | LB 0.46] with Only Raw EEG Signals in PyTorch, I thought maybe it's possible to improve the resnet1d_gru model from this <a href=\"https://www.kaggle.com/code/nischaydnk/hms-submission-1d-eegnet-pipeline-lightning\" target=\"_blank\">notebook</a>, I finally got CV 0.38 and LB 0.43.</p>\n<ul>\n<li>[LB 0.43] HMS Resnet1D-GRU Train](<a href=\"https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train\" target=\"_blank\">https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train</a>)</li>\n<li>[LB 0.43] HMS Resnet1D-GRU Inference](<a href=\"https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference\" target=\"_blank\">https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference</a>)</li>\n</ul>\n<p>Good Luck In The Competition.</p>",
  "messages": [
    {
      "id": 2660945,
      "postDate": "2024-02-20T22:26:26.600Z",
      "content": "<p>Hello everyone,</p>\n<p>After reading this forum, [CV 0.68 | LB 0.46] with Only Raw EEG Signals in PyTorch, I thought maybe it's possible to improve the resnet1d_gru model from this <a href=\"https://www.kaggle.com/code/nischaydnk/hms-submission-1d-eegnet-pipeline-lightning\" target=\"_blank\">notebook</a>, I finally got CV 0.38 and LB 0.43.</p>\n<ul>\n<li>[LB 0.43] HMS Resnet1D-GRU Train](<a href=\"https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train\" target=\"_blank\">https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train</a>)</li>\n<li>[LB 0.43] HMS Resnet1D-GRU Inference](<a href=\"https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference\" target=\"_blank\">https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference</a>)</li>\n</ul>\n<p>Good Luck In The Competition.</p>",
      "rawMarkdown": "Hello everyone,\n\nAfter reading this forum, [CV 0.68 | LB 0.46] with Only Raw EEG Signals in PyTorch, I thought maybe it's possible to improve the resnet1d_gru model from this [notebook](https://www.kaggle.com/code/nischaydnk/hms-submission-1d-eegnet-pipeline-lightning), I finally got CV 0.38 and LB 0.43.\n\n-  [LB 0.43] HMS Resnet1D-GRU Train](https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train)\n-  [LB 0.43] HMS Resnet1D-GRU Inference](https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference)\n\nGood Luck In The Competition.",
      "votes": 15
    },
    {
      "id": 2661589,
      "postDate": "2024-02-21T11:14:38.113Z",
      "content": "<p>You use completely different CV scheme — you cant compare the numbers!</p>",
      "rawMarkdown": "You use completely different CV scheme — you cant compare the numbers!",
      "votes": 4
    },
    {
      "id": 2661001,
      "postDate": "2024-02-21T00:14:46.820Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 2661589,
      "author_name": "Yurnero",
      "author_url": "",
      "post_date": "2024-02-21T11:14:38.113000",
      "content": "<p>You use completely different CV scheme — you cant compare the numbers!</p>",
      "votes": 4,
      "replies": []
    },
    {
      "id": 2661001,
      "author_name": "",
      "author_url": "",
      "post_date": "2024-02-21T00:14:46.820000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2660945": "Hello everyone,\n\nAfter reading this forum, [CV 0.68 | LB 0.46] with Only Raw EEG Signals in PyTorch, I thought maybe it's possible to improve the resnet1d_gru model from this [notebook](https://www.kaggle.com/code/nischaydnk/hms-submission-1d-eegnet-pipeline-lightning), I finally got CV 0.38 and LB 0.43.\n\n-  [LB 0.43] HMS Resnet1D-GRU Train](https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-train)\n-  [LB 0.43] HMS Resnet1D-GRU Inference](https://www.kaggle.com/code/medali1992/hms-resnet1d-gru-inference)\n\nGood Luck In The Competition.",
    "2661589": "You use completely different CV scheme — you cant compare the numbers!",
    "2661001": ""
  }
}