{
  "id": 398180,
  "title": "question on code requirements ",
  "url": "/competitions/birdclef-2023/discussion/398180",
  "author_name": "",
  "post_date": "2023-03-28T23:18:11.215422600Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I am new to kaggle competition. I noticed that many people separate train from infer notebooks. </p>\n<p>the \"code requirements\" of the competition states the following:</p>\n<ol>\n<li>CPU Notebook &lt;= 120 minutes run-time</li>\n<li>Freely &amp; publicly available external data is allowed, including pre-trained models</li>\n</ol>\n<p>does this 120-minute limit only apply to the infer notebook? if so, any model from the output of the train notebook should be made public available? </p>\n<p>thanks.</p>",
  "messages": [
    {
      "id": "2200934",
      "postDate": "03/28/2023 23:18:11",
      "content": "<p>I am new to kaggle competition. I noticed that many people separate train from infer notebooks. </p>\n<p>the \"code requirements\" of the competition states the following:</p>\n<ol>\n<li>CPU Notebook &lt;= 120 minutes run-time</li>\n<li>Freely &amp; publicly available external data is allowed, including pre-trained models</li>\n</ol>\n<p>does this 120-minute limit only apply to the infer notebook? if so, any model from the output of the train notebook should be made public available? </p>\n<p>thanks.</p>",
      "rawMarkdown": "I am new to kaggle competition. I noticed that many people separate train from infer notebooks. \n\nthe \"code requirements\" of the competition states the following:\n1. CPU Notebook <= 120 minutes run-time\n2. Freely & publicly available external data is allowed, including pre-trained models\n\ndoes this 120-minute limit only apply to the infer notebook? if so, any model from the output of the train notebook should be made public available? \n\nthanks.",
      "votes": null
    },
    {
      "id": "2201672",
      "postDate": "03/29/2023 13:34:04",
      "content": "<p>Yes the constraints are only for the infer notebook. And no it is not necessary, you can keep both your train and infer notebook private when submitting.</p>",
      "rawMarkdown": "Yes the constraints are only for the infer notebook. And no it is not necessary, you can keep both your train and infer notebook private when submitting.",
      "votes": null
    },
    {
      "id": "2204768",
      "postDate": "03/31/2023 23:08:06",
      "content": "<p>thank you very much!</p>",
      "rawMarkdown": "thank you very much!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2201672,
      "author_name": "lhanhsin",
      "author_url": "",
      "post_date": "03/29/2023 13:34:04",
      "content": "<p>Yes the constraints are only for the infer notebook. And no it is not necessary, you can keep both your train and infer notebook private when submitting.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2204768,
          "author_name": "jackxxu",
          "author_url": "",
          "post_date": "03/31/2023 23:08:06",
          "content": "<p>thank you very much!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2200934": "I am new to kaggle competition. I noticed that many people separate train from infer notebooks. \n\nthe \"code requirements\" of the competition states the following:\n1. CPU Notebook <= 120 minutes run-time\n2. Freely & publicly available external data is allowed, including pre-trained models\n\ndoes this 120-minute limit only apply to the infer notebook? if so, any model from the output of the train notebook should be made public available? \n\nthanks.",
    "2201672": "Yes the constraints are only for the infer notebook. And no it is not necessary, you can keep both your train and infer notebook private when submitting.",
    "2204768": "thank you very much!"
  },
  "source": "meta"
}