{
  "id": 68430,
  "title": "How are you addressing the special prize?",
  "url": "/competitions/human-protein-atlas-image-classification/discussion/68430",
  "author_name": "Brian",
  "post_date": "2018-10-12T15:51:22.133000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I see many kernel examples using pre-trained models with many millions of parameters. How would these work in the special prize on limited hardware? So far I am using a model with only 400K parameters, but I haven't been able to get it to perform great yet.</p>",
  "messages": [
    {
      "id": 402940,
      "postDate": "2018-10-12T15:51:22.133Z",
      "content": "<p>I see many kernel examples using pre-trained models with many millions of parameters. How would these work in the special prize on limited hardware? So far I am using a model with only 400K parameters, but I haven't been able to get it to perform great yet.</p>",
      "rawMarkdown": "I see many kernel examples using pre-trained models with many millions of parameters. How would these work in the special prize on limited hardware? So far I am using a model with only 400K parameters, but I haven't been able to get it to perform great yet.",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "402940": "I see many kernel examples using pre-trained models with many millions of parameters. How would these work in the special prize on limited hardware? So far I am using a model with only 400K parameters, but I haven't been able to get it to perform great yet."
  }
}