{
  "id": 33787,
  "title": "Help..What is pretrained model?",
  "url": "/competitions/intel-mobileodt-cervical-cancer-screening/discussion/33787",
  "author_name": "",
  "post_date": "2017-05-29T19:00:42.978921300Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I am new to kaggle and I just want to know what is this pretrained model which is told to be submitted.</p>",
  "messages": [
    {
      "id": "186930",
      "postDate": "05/29/2017 19:00:42",
      "content": "<p>I am new to kaggle and I just want to know what is this pretrained model which is told to be submitted.</p>",
      "rawMarkdown": "I am new to kaggle and I just want to know what is this pretrained model which is told to be submitted.",
      "votes": null
    },
    {
      "id": "187166",
      "postDate": "05/30/2017 16:16:36",
      "content": "<p>A pre-trained model is a model that has some or all of its weights learned by training on a different dataset than the one provided for this competition. ImageNet is probably the most popular dataset the models are 'pre-trained' on. The practice of training part of a deep network on one dataset and then using those weights as part of a predictive model for a different dataset is often called \"transfer learning\" (<a href=\"http://cs231n.github.io/transfer-learning/\">http://cs231n.github.io/transfer-learning/</a>).</p>",
      "rawMarkdown": "A pre-trained model is a model that has some or all of its weights learned by training on a different dataset than the one provided for this competition. ImageNet is probably the most popular dataset the models are 'pre-trained' on. The practice of training part of a deep network on one dataset and then using those weights as part of a predictive model for a different dataset is often called \"transfer learning\" (http://cs231n.github.io/transfer-learning/).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 187166,
      "author_name": "gkericks",
      "author_url": "",
      "post_date": "05/30/2017 16:16:36",
      "content": "<p>A pre-trained model is a model that has some or all of its weights learned by training on a different dataset than the one provided for this competition. ImageNet is probably the most popular dataset the models are 'pre-trained' on. The practice of training part of a deep network on one dataset and then using those weights as part of a predictive model for a different dataset is often called \"transfer learning\" (<a href=\"http://cs231n.github.io/transfer-learning/\">http://cs231n.github.io/transfer-learning/</a>).</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "186930": "I am new to kaggle and I just want to know what is this pretrained model which is told to be submitted.",
    "187166": "A pre-trained model is a model that has some or all of its weights learned by training on a different dataset than the one provided for this competition. ImageNet is probably the most popular dataset the models are 'pre-trained' on. The practice of training part of a deep network on one dataset and then using those weights as part of a predictive model for a different dataset is often called \"transfer learning\" (http://cs231n.github.io/transfer-learning/)."
  },
  "source": "meta"
}