{
  "id": 211335,
  "title": "Is it possible to use private pretrained models for making submission?",
  "url": "/competitions/ranzcr-clip-catheter-line-classification/discussion/211335",
  "author_name": "",
  "post_date": "2021-01-14T17:19:19.239664100Z",
  "votes": 3,
  "comment_count": 5,
  "views": 0,
  "content": "<p>I have trained a model in my workstation. Can i upload it as a private datasets and use it for making submissions? Will this violate code requirement policy?</p>\n<p>This doubt arise in my mind because code requirement policy says the following</p>\n<ul>\n<li>External data, freely &amp; publicly available, is allowed. This includes pretrained models.</li>\n</ul>",
  "messages": [
    {
      "id": "1153209",
      "postDate": "01/14/2021 17:19:19",
      "content": "<p>I have trained a model in my workstation. Can i upload it as a private datasets and use it for making submissions? Will this violate code requirement policy?</p>\n<p>This doubt arise in my mind because code requirement policy says the following</p>\n<ul>\n<li>External data, freely &amp; publicly available, is allowed. This includes pretrained models.</li>\n</ul>",
      "rawMarkdown": "I have trained a model in my workstation. Can i upload it as a private datasets and use it for making submissions? Will this violate code requirement policy?\n\nThis doubt arise in my mind because code requirement policy says the following\n- External data, freely & publicly available, is allowed. This includes pretrained models.",
      "votes": null
    },
    {
      "id": "1153392",
      "postDate": "01/14/2021 21:06:35",
      "content": "<p>Your own trained model is not external data. </p>",
      "rawMarkdown": "Your own trained model is not external data.",
      "votes": null
    },
    {
      "id": "1153593",
      "postDate": "01/15/2021 02:59:25",
      "content": "<p>Yes.</p>\n<ol>\n<li>train your model in your own server</li>\n<li>upload your weight. You need to make a notebook and a dataset in which your weight is uploaded.</li>\n<li>inference with your weight.</li>\n<li>submit. </li>\n</ol>",
      "rawMarkdown": "Yes.\n\n1. train your model in your own server\n2. upload your weight. You need to make a notebook and a dataset in which your weight is uploaded.\n3. inference with your weight.\n4. submit.",
      "votes": null
    },
    {
      "id": "1153770",
      "postDate": "01/15/2021 06:32:50",
      "content": "<p>make sense. Thank You</p>",
      "rawMarkdown": "make sense. Thank You",
      "votes": null
    },
    {
      "id": "1153771",
      "postDate": "01/15/2021 06:33:06",
      "content": "<p>Thank You.</p>",
      "rawMarkdown": "Thank You.",
      "votes": null
    },
    {
      "id": "1194286",
      "postDate": "02/10/2021 06:18:55",
      "content": "<p>Then, why there is a \"CPU Notebook &lt;= 9 hours run-time\" Competition requirement. We can train hours and hours then upload our model. Is it means \"Dont use Kaggle Notebook more than 9 hours\"?</p>\n<p>Thanks. </p>",
      "rawMarkdown": "Then, why there is a \"CPU Notebook <= 9 hours run-time\" Competition requirement. We can train hours and hours then upload our model. Is it means \"Dont use Kaggle Notebook more than 9 hours\"?\n\nThanks.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1153392,
      "author_name": "richardepstein",
      "author_url": "",
      "post_date": "01/14/2021 21:06:35",
      "content": "<p>Your own trained model is not external data. </p>",
      "votes": null,
      "replies": [
        {
          "id": 1153770,
          "author_name": "aravindpadman",
          "author_url": "",
          "post_date": "01/15/2021 06:32:50",
          "content": "<p>make sense. Thank You</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1153593,
      "author_name": "youhanlee",
      "author_url": "",
      "post_date": "01/15/2021 02:59:25",
      "content": "<p>Yes.</p>\n<ol>\n<li>train your model in your own server</li>\n<li>upload your weight. You need to make a notebook and a dataset in which your weight is uploaded.</li>\n<li>inference with your weight.</li>\n<li>submit. </li>\n</ol>",
      "votes": null,
      "replies": [
        {
          "id": 1153771,
          "author_name": "aravindpadman",
          "author_url": "",
          "post_date": "01/15/2021 06:33:06",
          "content": "<p>Thank You.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1194286,
          "author_name": "tcallioglu",
          "author_url": "",
          "post_date": "02/10/2021 06:18:55",
          "content": "<p>Then, why there is a \"CPU Notebook &lt;= 9 hours run-time\" Competition requirement. We can train hours and hours then upload our model. Is it means \"Dont use Kaggle Notebook more than 9 hours\"?</p>\n<p>Thanks. </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1153209": "I have trained a model in my workstation. Can i upload it as a private datasets and use it for making submissions? Will this violate code requirement policy?\n\nThis doubt arise in my mind because code requirement policy says the following\n- External data, freely & publicly available, is allowed. This includes pretrained models.",
    "1153392": "Your own trained model is not external data.",
    "1153593": "Yes.\n\n1. train your model in your own server\n2. upload your weight. You need to make a notebook and a dataset in which your weight is uploaded.\n3. inference with your weight.\n4. submit.",
    "1153770": "make sense. Thank You",
    "1153771": "Thank You.",
    "1194286": "Then, why there is a \"CPU Notebook <= 9 hours run-time\" Competition requirement. We can train hours and hours then upload our model. Is it means \"Dont use Kaggle Notebook more than 9 hours\"?\n\nThanks."
  },
  "source": "meta"
}