{
  "id": 134158,
  "title": "Should submission notebook include training script?",
  "url": "/competitions/deepfake-detection-challenge/discussion/134158",
  "author_name": "",
  "post_date": "2020-03-06T10:47:37.829533600Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hello, I am new to Kaggle and my question is that submission notebook should include training script.</p>\n\n<p>This competition has code requirements as bellows. \n <code>\nCPU Notebook &lt;= 9 hours run-time\nGPU Notebook &lt;= 9 hours run-time on Kaggle's P100 GPUs\n</code>\nIs this time limit only for prediction? or including training time? I find that there are training videos in submission notebook so I wonder that this time limit includes training time.</p>",
  "messages": [
    {
      "id": "765188",
      "postDate": "03/06/2020 10:47:37",
      "content": "<p>Hello, I am new to Kaggle and my question is that submission notebook should include training script.</p>\n\n<p>This competition has code requirements as bellows. \n <code>\nCPU Notebook &lt;= 9 hours run-time\nGPU Notebook &lt;= 9 hours run-time on Kaggle's P100 GPUs\n</code>\nIs this time limit only for prediction? or including training time? I find that there are training videos in submission notebook so I wonder that this time limit includes training time.</p>",
      "rawMarkdown": "Hello, I am new to Kaggle and my question is that submission notebook should include training script.\n\nThis competition has code requirements as bellows. \n ```\nCPU Notebook &lt;= 9 hours run-time\nGPU Notebook &lt;= 9 hours run-time on Kaggle's P100 GPUs\n```\nIs this time limit only for prediction? or including training time? I find that there are training videos in submission notebook so I wonder that this time limit includes training time.",
      "votes": null
    },
    {
      "id": "765217",
      "postDate": "03/06/2020 11:51:10",
      "content": "<p>best practices, will be used for prediction time, u can add offline trained models as datasets </p>",
      "rawMarkdown": "best practices, will be used for prediction time, u can add offline trained models as datasets",
      "votes": null
    },
    {
      "id": "765244",
      "postDate": "03/06/2020 12:14:40",
      "content": "<p>No, it does not include training time. You should put your trained model into a new dataset, then load it in your inference notebook.</p>",
      "rawMarkdown": "No, it does not include training time. You should put your trained model into a new dataset, then load it in your inference notebook.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 765217,
      "author_name": "seshurajup",
      "author_url": "",
      "post_date": "03/06/2020 11:51:10",
      "content": "<p>best practices, will be used for prediction time, u can add offline trained models as datasets </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 765244,
      "author_name": "humananalog",
      "author_url": "",
      "post_date": "03/06/2020 12:14:40",
      "content": "<p>No, it does not include training time. You should put your trained model into a new dataset, then load it in your inference notebook.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "765188": "Hello, I am new to Kaggle and my question is that submission notebook should include training script.\n\nThis competition has code requirements as bellows. \n ```\nCPU Notebook &lt;= 9 hours run-time\nGPU Notebook &lt;= 9 hours run-time on Kaggle's P100 GPUs\n```\nIs this time limit only for prediction? or including training time? I find that there are training videos in submission notebook so I wonder that this time limit includes training time.",
    "765217": "best practices, will be used for prediction time, u can add offline trained models as datasets",
    "765244": "No, it does not include training time. You should put your trained model into a new dataset, then load it in your inference notebook."
  },
  "source": "meta"
}