{
  "id": 40937,
  "title": "tricks",
  "url": "/competitions/cdiscount-image-classification-challenge/discussion/40937",
  "author_name": "",
  "post_date": "2017-10-10T13:55:09.225199200Z",
  "votes": 15,
  "comment_count": 4,
  "views": 0,
  "content": "<p>you can google for more, e.g. \"imagenet + tricks\". check also imagenet challenge website.\nhere are some examples</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/229793/7580/trick_5.png\" alt=\"enter image description here\" title=\"\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/229793/7582/trick_1.png\" alt=\"enter image description here\" title=\"\"></p>",
  "messages": [
    {
      "id": "229793",
      "postDate": "10/10/2017 13:55:09",
      "content": "<p>you can google for more, e.g. \"imagenet + tricks\". check also imagenet challenge website.\nhere are some examples</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/229793/7580/trick_5.png\" alt=\"enter image description here\" title=\"\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/229793/7582/trick_1.png\" alt=\"enter image description here\" title=\"\"></p>",
      "rawMarkdown": "you can google for more, e.g. \"imagenet + tricks\". check also imagenet challenge website.\nhere are some examples\n\n ![enter image description here][1]\n\n ![enter image description here][2]\n\n\n  [1]: https://kaggle2.blob.core.windows.net/forum-message-attachments/229793/7580/trick_5.png\n  [2]: https://kaggle2.blob.core.windows.net/forum-message-attachments/229793/7582/trick_1.png",
      "votes": null
    },
    {
      "id": "229808",
      "postDate": "10/10/2017 14:36:40",
      "content": "<p>Thank you for your great sharing. </p>",
      "rawMarkdown": "Thank you for your great sharing.",
      "votes": null
    },
    {
      "id": "229938",
      "postDate": "10/10/2017 20:11:24",
      "content": "<p>check also this:\n<a href=\"https://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion\">https://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion</a></p>",
      "rawMarkdown": "check also this:\nhttps://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion",
      "votes": null
    },
    {
      "id": "229969",
      "postDate": "10/10/2017 23:00:48",
      "content": "<p>Thx for sharing!</p>",
      "rawMarkdown": "Thx for sharing!",
      "votes": null
    },
    {
      "id": "230451",
      "postDate": "10/12/2017 00:36:35",
      "content": "<p><a href=\"http://places2.csail.mit.edu/results2016.html\">http://places2.csail.mit.edu/results2016.html</a></p>\n\n<p>\"Moreover, we utilize balanced sampling strategy [2] and label smooth regularization [5] during training, to alleviate the bias from the non-uniform sample distribution among categories and partial incorrect training labels. \"</p>",
      "rawMarkdown": "http://places2.csail.mit.edu/results2016.html\n\n\"Moreover, we utilize balanced sampling strategy [2] and label smooth regularization [5] during training, to alleviate the bias from the non-uniform sample distribution among categories and partial incorrect training labels. \"",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 229808,
      "author_name": "qinhui1999",
      "author_url": "",
      "post_date": "10/10/2017 14:36:40",
      "content": "<p>Thank you for your great sharing. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 229938,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "10/10/2017 20:11:24",
      "content": "<p>check also this:\n<a href=\"https://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion\">https://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 229969,
      "author_name": "brianlzm",
      "author_url": "",
      "post_date": "10/10/2017 23:00:48",
      "content": "<p>Thx for sharing!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 230451,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "10/12/2017 00:36:35",
      "content": "<p><a href=\"http://places2.csail.mit.edu/results2016.html\">http://places2.csail.mit.edu/results2016.html</a></p>\n\n<p>\"Moreover, we utilize balanced sampling strategy [2] and label smooth regularization [5] during training, to alleviate the bias from the non-uniform sample distribution among categories and partial incorrect training labels. \"</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "229793": "you can google for more, e.g. \"imagenet + tricks\". check also imagenet challenge website.\nhere are some examples\n\n ![enter image description here][1]\n\n ![enter image description here][2]\n\n\n  [1]: https://kaggle2.blob.core.windows.net/forum-message-attachments/229793/7580/trick_5.png\n  [2]: https://kaggle2.blob.core.windows.net/forum-message-attachments/229793/7582/trick_1.png",
    "229808": "Thank you for your great sharing.",
    "229938": "check also this:\nhttps://www.kaggle.com/c/inaturalist-challenge-at-fgvc-2017/discussion",
    "229969": "Thx for sharing!",
    "230451": "http://places2.csail.mit.edu/results2016.html\n\n\"Moreover, we utilize balanced sampling strategy [2] and label smooth regularization [5] during training, to alleviate the bias from the non-uniform sample distribution among categories and partial incorrect training labels. \""
  },
  "source": "meta"
}