{
  "id": 575320,
  "title": "submission threw exception while the interactive and commit version both successfully.",
  "url": "/competitions/byu-locating-bacterial-flagellar-motors-2025/discussion/575320",
  "author_name": "",
  "post_date": "2025-04-27T17:49:51.389443800Z",
  "votes": 1,
  "comment_count": 6,
  "views": 0,
  "content": "<p>what is the reason?  I tried a new model. </p>\n<p>This does not happened to other models.</p>\n<p>Any hints?</p>",
  "messages": [
    {
      "id": "3188502",
      "postDate": "04/27/2025 17:49:51",
      "content": "<p>what is the reason?  I tried a new model. </p>\n<p>This does not happened to other models.</p>\n<p>Any hints?</p>",
      "rawMarkdown": "what is the reason?  I tried a new model. \n\nThis does not happened to other models.\n\nAny hints?",
      "votes": null
    },
    {
      "id": "3188703",
      "postDate": "04/28/2025 04:23:54",
      "content": "<p>I have the exact same situation, Didn't find a solution yet for that particular model. </p>",
      "rawMarkdown": "I have the exact same situation, Didn't find a solution yet for that particular model.",
      "votes": null
    },
    {
      "id": "3188746",
      "postDate": "04/28/2025 06:11:59",
      "content": "<p>DEIM for me.</p>",
      "rawMarkdown": "DEIM for me.",
      "votes": null
    },
    {
      "id": "3189665",
      "postDate": "04/29/2025 15:07:55",
      "content": "<p>Any information on the model?  It could be a mismatch in input size, mismatch in expected output format, unable to load when using no internet, out of memory if its larger, and so on.  If it works in the commit and interactive but breaks in submission then it is likely due to the fact that it is unable to process the larger amount of data that is in the hidden dataset as that is the only possibility.</p>",
      "rawMarkdown": "Any information on the model?  It could be a mismatch in input size, mismatch in expected output format, unable to load when using no internet, out of memory if its larger, and so on.  If it works in the commit and interactive but breaks in submission then it is likely due to the fact that it is unable to process the larger amount of data that is in the hidden dataset as that is the only possibility.",
      "votes": null
    },
    {
      "id": "3190455",
      "postDate": "04/30/2025 17:22:54",
      "content": "<p>I forked a public submission notebook, just changing the model.  no other info except threw exception after submitting a few mintues.</p>\n<p>I will try to change batch prediction to one by one, if that will work or not.</p>",
      "rawMarkdown": "I forked a public submission notebook, just changing the model.  no other info except threw exception after submitting a few mintues.\n\nI will try to change batch prediction to one by one, if that will work or not.",
      "votes": null
    },
    {
      "id": "3190469",
      "postDate": "04/30/2025 17:35:44",
      "content": "<p>Rreducing batch size will  lead to  out of time based on estimation.</p>",
      "rawMarkdown": "Rreducing batch size will  lead to  out of time based on estimation.",
      "votes": null
    },
    {
      "id": "3191747",
      "postDate": "05/02/2025 05:21:04",
      "content": "<p>here is the notebook</p>\n<p><a href=\"https://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009\" target=\"_blank\">https://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009</a></p>",
      "rawMarkdown": "here is the notebook\n\nhttps://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3188703,
      "author_name": "iamudit",
      "author_url": "",
      "post_date": "04/28/2025 04:23:54",
      "content": "<p>I have the exact same situation, Didn't find a solution yet for that particular model. </p>",
      "votes": null,
      "replies": [
        {
          "id": 3188746,
          "author_name": "dragonzhang",
          "author_url": "",
          "post_date": "04/28/2025 06:11:59",
          "content": "<p>DEIM for me.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 3189665,
      "author_name": "connorjd",
      "author_url": "",
      "post_date": "04/29/2025 15:07:55",
      "content": "<p>Any information on the model?  It could be a mismatch in input size, mismatch in expected output format, unable to load when using no internet, out of memory if its larger, and so on.  If it works in the commit and interactive but breaks in submission then it is likely due to the fact that it is unable to process the larger amount of data that is in the hidden dataset as that is the only possibility.</p>",
      "votes": null,
      "replies": [
        {
          "id": 3190455,
          "author_name": "dragonzhang",
          "author_url": "",
          "post_date": "04/30/2025 17:22:54",
          "content": "<p>I forked a public submission notebook, just changing the model.  no other info except threw exception after submitting a few mintues.</p>\n<p>I will try to change batch prediction to one by one, if that will work or not.</p>",
          "votes": null,
          "replies": [
            {
              "id": 3190469,
              "author_name": "dragonzhang",
              "author_url": "",
              "post_date": "04/30/2025 17:35:44",
              "content": "<p>Rreducing batch size will  lead to  out of time based on estimation.</p>",
              "votes": null,
              "replies": []
            }
          ]
        },
        {
          "id": 3191747,
          "author_name": "dragonzhang",
          "author_url": "",
          "post_date": "05/02/2025 05:21:04",
          "content": "<p>here is the notebook</p>\n<p><a href=\"https://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009\" target=\"_blank\">https://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009</a></p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "3188502": "what is the reason?  I tried a new model. \n\nThis does not happened to other models.\n\nAny hints?",
    "3188703": "I have the exact same situation, Didn't find a solution yet for that particular model.",
    "3188746": "DEIM for me.",
    "3189665": "Any information on the model?  It could be a mismatch in input size, mismatch in expected output format, unable to load when using no internet, out of memory if its larger, and so on.  If it works in the commit and interactive but breaks in submission then it is likely due to the fact that it is unable to process the larger amount of data that is in the hidden dataset as that is the only possibility.",
    "3190455": "I forked a public submission notebook, just changing the model.  no other info except threw exception after submitting a few mintues.\n\nI will try to change batch prediction to one by one, if that will work or not.",
    "3190469": "Rreducing batch size will  lead to  out of time based on estimation.",
    "3191747": "here is the notebook\n\nhttps://www.kaggle.com/code/dragonzhang/deimkit-offline-infer-demo?scriptVersionId=237076009"
  },
  "source": "meta"
}