{
  "id": 43830,
  "title": "Low accuracy problem",
  "url": "/competitions/dogs-vs-cats/discussion/43830",
  "author_name": "",
  "post_date": "2017-11-20T12:52:51.503838300Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p><strong>Hi everyone,</strong> \nI'm trying to make a classificator for this dataset resizing and grayscaling the images so that each image become a vector of length width*hight. Im using random forest and unfortunetly the best result I've got so far is 65% accuracy. \nDo you guys have an advise of how i can reach 70% accuracy ?\nThanks !   </p>",
  "messages": [
    {
      "id": "246054",
      "postDate": "11/20/2017 12:52:51",
      "content": "<p><strong>Hi everyone,</strong> \nI'm trying to make a classificator for this dataset resizing and grayscaling the images so that each image become a vector of length width*hight. Im using random forest and unfortunetly the best result I've got so far is 65% accuracy. \nDo you guys have an advise of how i can reach 70% accuracy ?\nThanks !   </p>",
      "rawMarkdown": "**Hi everyone,** \nI'm trying to make a classificator for this dataset resizing and grayscaling the images so that each image become a vector of length width*hight. Im using random forest and unfortunetly the best result I've got so far is 65% accuracy. \nDo you guys have an advise of how i can reach 70% accuracy ?\nThanks !",
      "votes": null
    },
    {
      "id": "248887",
      "postDate": "11/27/2017 07:25:55",
      "content": "<p>Just out of curiosity, why are you using Random Forest for this problem? Try using convolutional NNs and you should easily get to ~85% accuracy in the first go! Also, read about why CNNs are better for problems like this one.</p>\n\n<p>I'm no expert, but hope this helps! Cheers.</p>",
      "rawMarkdown": "Just out of curiosity, why are you using Random Forest for this problem? Try using convolutional NNs and you should easily get to ~85% accuracy in the first go! Also, read about why CNNs are better for problems like this one.\n\nI'm no expert, but hope this helps! Cheers.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 248887,
      "author_name": "sid2364",
      "author_url": "",
      "post_date": "11/27/2017 07:25:55",
      "content": "<p>Just out of curiosity, why are you using Random Forest for this problem? Try using convolutional NNs and you should easily get to ~85% accuracy in the first go! Also, read about why CNNs are better for problems like this one.</p>\n\n<p>I'm no expert, but hope this helps! Cheers.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "246054": "**Hi everyone,** \nI'm trying to make a classificator for this dataset resizing and grayscaling the images so that each image become a vector of length width*hight. Im using random forest and unfortunetly the best result I've got so far is 65% accuracy. \nDo you guys have an advise of how i can reach 70% accuracy ?\nThanks !",
    "248887": "Just out of curiosity, why are you using Random Forest for this problem? Try using convolutional NNs and you should easily get to ~85% accuracy in the first go! Also, read about why CNNs are better for problems like this one.\n\nI'm no expert, but hope this helps! Cheers."
  },
  "source": "meta"
}