{
  "id": 413787,
  "title": "Models with variable output sizes",
  "url": "/competitions/asl-fingerspelling/discussion/413787",
  "author_name": "Nathan Zhao",
  "post_date": "2023-05-30T05:14:03.379000",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Based on current submission attempts (see <a href=\"https://www.kaggle.com/anokas\" target=\"_blank\">@anokas</a> notebook <a href=\"https://www.kaggle.com/code/anokas/static-greedy-baseline-0-157-lb\" target=\"_blank\">here</a>), it seems like we need a model with variable output sizes. What are some possible models for this?</p>",
  "messages": [
    {
      "id": 2280402,
      "postDate": "2023-05-30T05:14:03.380Z",
      "content": "<p>Based on current submission attempts (see <a href=\"https://www.kaggle.com/anokas\" target=\"_blank\">@anokas</a> notebook <a href=\"https://www.kaggle.com/code/anokas/static-greedy-baseline-0-157-lb\" target=\"_blank\">here</a>), it seems like we need a model with variable output sizes. What are some possible models for this?</p>",
      "rawMarkdown": "Based on current submission attempts (see @anokas notebook [here](https://www.kaggle.com/code/anokas/static-greedy-baseline-0-157-lb)), it seems like we need a model with variable output sizes. What are some possible models for this?",
      "votes": 1
    },
    {
      "id": 2280846,
      "postDate": "2023-05-30T12:17:35.503Z",
      "content": "<p>CTC loss is suitable for this.</p>",
      "rawMarkdown": "CTC loss is suitable for this.",
      "replies": [
        {
          "id": 2281881,
          "postDate": "2023-05-31T07:48:46.543Z",
          "content": "<p>Here is my <a href=\"https://www.kaggle.com/competitions/asl-fingerspelling/discussion/409512\" target=\"_blank\">discussion regarding CTC loss</a></p>",
          "rawMarkdown": "Here is my [discussion regarding CTC loss](https://www.kaggle.com/competitions/asl-fingerspelling/discussion/409512)"
        }
      ]
    }
  ],
  "comments": [
    {
      "id": 2280846,
      "author_name": "stk2666",
      "author_url": "",
      "post_date": "2023-05-30T12:17:35.503000",
      "content": "<p>CTC loss is suitable for this.</p>",
      "votes": 0,
      "replies": [
        {
          "id": 2281881,
          "author_name": "Mykola",
          "author_url": "",
          "post_date": "2023-05-31T07:48:46.543000",
          "content": "<p>Here is my <a href=\"https://www.kaggle.com/competitions/asl-fingerspelling/discussion/409512\" target=\"_blank\">discussion regarding CTC loss</a></p>",
          "votes": 0,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2280402": "Based on current submission attempts (see @anokas notebook [here](https://www.kaggle.com/code/anokas/static-greedy-baseline-0-157-lb)), it seems like we need a model with variable output sizes. What are some possible models for this?",
    "2280846": "CTC loss is suitable for this."
  }
}