{
  "id": 419351,
  "title": "Problem with understanding the concept of Sequecne Id and Frame length",
  "url": "/competitions/asl-fingerspelling/discussion/419351",
  "author_name": "Arka Bhowmick",
  "post_date": "2023-06-25T12:44:16.154000",
  "votes": 0,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello everyone,<br>\nI am having a bit of difficulty in understanding the following concept. For each sequence Id there are variable number of frames. Now if I consider that each sequence is a video sequence with say X number of frames, does that mean that the full sequence is  necessary in order to create the target phrase? And if that is true, then how may I create a dataset that has uniform number of frames. It is not possible. Any kind of guidance will be really helpful.<br>\nBest Regards,<br>\nArka</p>",
  "messages": [
    {
      "id": 2317645,
      "postDate": "2023-06-25T20:53:54.953Z",
      "content": "<p>Check the most popular notebooks in the Code section, there are several examples there how to do it.</p>",
      "rawMarkdown": "Check the most popular notebooks in the Code section, there are several examples there how to do it.",
      "votes": 1
    },
    {
      "id": 2317096,
      "postDate": "2023-06-25T12:44:16.153Z",
      "content": "<p>Hello everyone,<br>\nI am having a bit of difficulty in understanding the following concept. For each sequence Id there are variable number of frames. Now if I consider that each sequence is a video sequence with say X number of frames, does that mean that the full sequence is  necessary in order to create the target phrase? And if that is true, then how may I create a dataset that has uniform number of frames. It is not possible. Any kind of guidance will be really helpful.<br>\nBest Regards,<br>\nArka</p>",
      "rawMarkdown": "Hello everyone,\nI am having a bit of difficulty in understanding the following concept. For each sequence Id there are variable number of frames. Now if I consider that each sequence is a video sequence with say X number of frames, does that mean that the full sequence is  necessary in order to create the target phrase? And if that is true, then how may I create a dataset that has uniform number of frames. It is not possible. Any kind of guidance will be really helpful.\nBest Regards,\nArka"
    }
  ],
  "comments": [
    {
      "id": 2317645,
      "author_name": "greySnow",
      "author_url": "",
      "post_date": "2023-06-25T20:53:54.953000",
      "content": "<p>Check the most popular notebooks in the Code section, there are several examples there how to do it.</p>",
      "votes": 1,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2317645": "Check the most popular notebooks in the Code section, there are several examples there how to do it.",
    "2317096": "Hello everyone,\nI am having a bit of difficulty in understanding the following concept. For each sequence Id there are variable number of frames. Now if I consider that each sequence is a video sequence with say X number of frames, does that mean that the full sequence is  necessary in order to create the target phrase? And if that is true, then how may I create a dataset that has uniform number of frames. It is not possible. Any kind of guidance will be really helpful.\nBest Regards,\nArka"
  }
}