{
  "id": 29911,
  "title": "Discussion of different approaches!",
  "url": "/competitions/dogs-vs-cats-redux-kernels-edition/discussion/29911",
  "author_name": "prajwalkr",
  "post_date": "2017-03-11T12:24:50.308000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi</p>\n\n<p>I tried really hard to go beyond #60th position, but could not go beyond. I used pretrained ResNet50 and InceptionV3 models and trained a classifier on top of them. I averaged the predictions of the models to get a logloss of 0.04973 on the Kaggle leaderboard.</p>\n\n<p>I would like to know what other different approaches people tried out to get a better score.</p>\n\n<p>Thanks.</p>",
  "messages": [
    {
      "id": 166846,
      "postDate": "2017-03-11T12:24:50.307Z",
      "content": "<p>Hi</p>\n\n<p>I tried really hard to go beyond #60th position, but could not go beyond. I used pretrained ResNet50 and InceptionV3 models and trained a classifier on top of them. I averaged the predictions of the models to get a logloss of 0.04973 on the Kaggle leaderboard.</p>\n\n<p>I would like to know what other different approaches people tried out to get a better score.</p>\n\n<p>Thanks.</p>",
      "rawMarkdown": "Hi\n\nI tried really hard to go beyond #60th position, but could not go beyond. I used pretrained ResNet50 and InceptionV3 models and trained a classifier on top of them. I averaged the predictions of the models to get a logloss of 0.04973 on the Kaggle leaderboard.\n\nI would like to know what other different approaches people tried out to get a better score.\n\nThanks.",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "166846": "Hi\n\nI tried really hard to go beyond #60th position, but could not go beyond. I used pretrained ResNet50 and InceptionV3 models and trained a classifier on top of them. I averaged the predictions of the models to get a logloss of 0.04973 on the Kaggle leaderboard.\n\nI would like to know what other different approaches people tried out to get a better score.\n\nThanks."
  }
}