{
  "id": 138795,
  "title": "Someone help clarify these two rules for me? (external code/data)",
  "url": "/competitions/deepfake-detection-challenge/discussion/138795",
  "author_name": "",
  "post_date": "2020-03-26T11:28:49.367850700Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi, \nI wanna make sure i have everything correctly. If I have xception model implementation (publicly available on github ofc) as data I have added to the notebook, does that break these two rules below? In my code, I have to basically switch to the folders to import necessary functions then switch back. If its a problem, I will just paste the code in the notebook, which sounds like it should be enough?</p>\n\n<p>The rules:\n- No using other Kaggle notebooks or utility scripts as inputs to your submission notebook. External data also cannot be externally-referenced (i.e. via BigQuery, Github, external URL). Instead, load external models or datasets directly as an external data source.\n- No custom packages enabled in your submission notebook</p>",
  "messages": [
    {
      "id": "786943",
      "postDate": "03/26/2020 11:28:49",
      "content": "<p>Hi, \nI wanna make sure i have everything correctly. If I have xception model implementation (publicly available on github ofc) as data I have added to the notebook, does that break these two rules below? In my code, I have to basically switch to the folders to import necessary functions then switch back. If its a problem, I will just paste the code in the notebook, which sounds like it should be enough?</p>\n\n<p>The rules:\n- No using other Kaggle notebooks or utility scripts as inputs to your submission notebook. External data also cannot be externally-referenced (i.e. via BigQuery, Github, external URL). Instead, load external models or datasets directly as an external data source.\n- No custom packages enabled in your submission notebook</p>",
      "rawMarkdown": "Hi, \nI wanna make sure i have everything correctly. If I have xception model implementation (publicly available on github ofc) as data I have added to the notebook, does that break these two rules below? In my code, I have to basically switch to the folders to import necessary functions then switch back. If its a problem, I will just paste the code in the notebook, which sounds like it should be enough?\n\nThe rules:\n- No using other Kaggle notebooks or utility scripts as inputs to your submission notebook. External data also cannot be externally-referenced (i.e. via BigQuery, Github, external URL). Instead, load external models or datasets directly as an external data source.\n- No custom packages enabled in your submission notebook",
      "votes": null
    },
    {
      "id": "786944",
      "postDate": "03/26/2020 11:29:17",
      "content": "<p>feel free to link an earlier thread if it has been discussed :)</p>",
      "rawMarkdown": "feel free to link an earlier thread if it has been discussed :)",
      "votes": null
    },
    {
      "id": "786956",
      "postDate": "03/26/2020 11:42:49",
      "content": "<p><a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756\">https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756</a> I guess its fine? :D </p>",
      "rawMarkdown": "https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756 I guess its fine? :D",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 786944,
      "author_name": "ipekgani",
      "author_url": "",
      "post_date": "03/26/2020 11:29:17",
      "content": "<p>feel free to link an earlier thread if it has been discussed :)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 786956,
      "author_name": "ipekgani",
      "author_url": "",
      "post_date": "03/26/2020 11:42:49",
      "content": "<p><a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756\">https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756</a> I guess its fine? :D </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "786943": "Hi, \nI wanna make sure i have everything correctly. If I have xception model implementation (publicly available on github ofc) as data I have added to the notebook, does that break these two rules below? In my code, I have to basically switch to the folders to import necessary functions then switch back. If its a problem, I will just paste the code in the notebook, which sounds like it should be enough?\n\nThe rules:\n- No using other Kaggle notebooks or utility scripts as inputs to your submission notebook. External data also cannot be externally-referenced (i.e. via BigQuery, Github, external URL). Instead, load external models or datasets directly as an external data source.\n- No custom packages enabled in your submission notebook",
    "786944": "feel free to link an earlier thread if it has been discussed :)",
    "786956": "https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121203#779756 I guess its fine? :D"
  },
  "source": "meta"
}