{
  "id": 97863,
  "title": "New Insights",
  "url": "/competitions/generative-dog-images/discussion/97863",
  "author_name": "",
  "post_date": "2019-06-29T09:52:41.905896700Z",
  "votes": 16,
  "comment_count": 6,
  "views": 0,
  "content": "<p>Thanks to Vitaliy and his kernel <a href=\"https://www.kaggle.com/witold1/quick-data-explanation-and-eda\">Quick data explanation and EDA</a></p>\n\n<h3><a href=\"http://vision.stanford.edu/aditya86/ImageNetDogs/\">Stanford Dogs Dataset</a></h3>\n\n<p>The Stanford Dogs dataset contains images of <strong>120 breeds</strong> of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. Contents of this dataset:</p>\n\n<ul>\n<li>Number of categories: 120</li>\n<li>Number of images: 20,580</li>\n<li>Annotations: Class labels, Bounding boxes</li>\n</ul>\n\n<p>We have  20579 pictures</p>\n\n<h3>Interesting data facts are</h3>\n\n<ul>\n<li>There are pictures with more than one dog (even with  <strong>3  dogs</strong>);</li>\n<li>There are pictures with the dog (-s) and person (people);</li>\n<li>There are pictures with more than one person (even with  <strong>4  people</strong>);</li>\n<li>There are pictures where dogs occupy less than  1/5  of the picture;</li>\n<li>There are pictures with text (magazine covers, from dog shows, memes and pictures with text);</li>\n<li>Even wild predators included, e.g. African wild dog or Dingo, but not wolves.</li>\n</ul>\n\n<h3>Examples</h3>\n\n<p><img src=\"https://i.ibb.co/1ZytPCk/results-6-1.png\" alt=\"results-6-1\">\n<img src=\"https://i.ibb.co/rdv6Q9M/descarga.png\" alt=\"descarga\"></p>\n\n<p>Maybe knowledge of breeds features, distribution of photos and visual analysis of pictures may help in this task of an image generation, delete the pictures with persons or 3 dogs ...\n<strong>But</strong></p>\n\n<p>&gt; Imagenet pre-trained models are NOT allowed</p>\n\n<p>check: <a href=\"https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334\">https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334</a></p>",
  "messages": [
    {
      "id": "564347",
      "postDate": "06/29/2019 09:52:41",
      "content": "<p>Thanks to Vitaliy and his kernel <a href=\"https://www.kaggle.com/witold1/quick-data-explanation-and-eda\">Quick data explanation and EDA</a></p>\n\n<h3><a href=\"http://vision.stanford.edu/aditya86/ImageNetDogs/\">Stanford Dogs Dataset</a></h3>\n\n<p>The Stanford Dogs dataset contains images of <strong>120 breeds</strong> of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. Contents of this dataset:</p>\n\n<ul>\n<li>Number of categories: 120</li>\n<li>Number of images: 20,580</li>\n<li>Annotations: Class labels, Bounding boxes</li>\n</ul>\n\n<p>We have  20579 pictures</p>\n\n<h3>Interesting data facts are</h3>\n\n<ul>\n<li>There are pictures with more than one dog (even with  <strong>3  dogs</strong>);</li>\n<li>There are pictures with the dog (-s) and person (people);</li>\n<li>There are pictures with more than one person (even with  <strong>4  people</strong>);</li>\n<li>There are pictures where dogs occupy less than  1/5  of the picture;</li>\n<li>There are pictures with text (magazine covers, from dog shows, memes and pictures with text);</li>\n<li>Even wild predators included, e.g. African wild dog or Dingo, but not wolves.</li>\n</ul>\n\n<h3>Examples</h3>\n\n<p><img src=\"https://i.ibb.co/1ZytPCk/results-6-1.png\" alt=\"results-6-1\">\n<img src=\"https://i.ibb.co/rdv6Q9M/descarga.png\" alt=\"descarga\"></p>\n\n<p>Maybe knowledge of breeds features, distribution of photos and visual analysis of pictures may help in this task of an image generation, delete the pictures with persons or 3 dogs ...\n<strong>But</strong></p>\n\n<p>&gt; Imagenet pre-trained models are NOT allowed</p>\n\n<p>check: <a href=\"https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334\">https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334</a></p>",
      "rawMarkdown": "Thanks to [Vitaliy](@witold1) and his kernel [Quick data explanation and EDA](https://www.kaggle.com/witold1/quick-data-explanation-and-eda)\n\n### [Stanford Dogs Dataset](http://vision.stanford.edu/aditya86/ImageNetDogs/)\n\nThe Stanford Dogs dataset contains images of **120 breeds** of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. Contents of this dataset:\n\n- Number of categories: 120\n- Number of images: 20,580\n- Annotations: Class labels, Bounding boxes\n\nWe have  20579 pictures\n\n### Interesting data facts are\n\n- There are pictures with more than one dog (even with  **3  dogs**);\n- There are pictures with the dog (-s) and person (people);\n- There are pictures with more than one person (even with  **4  people**);\n- There are pictures where dogs occupy less than  1/5  of the picture;\n- There are pictures with text (magazine covers, from dog shows, memes and pictures with text);\n- Even wild predators included, e.g. African wild dog or Dingo, but not wolves.\n\n### Examples\n\n<img src=\"https://i.ibb.co/1ZytPCk/results-6-1.png\" alt=\"results-6-1\">\n<img src=\"https://i.ibb.co/rdv6Q9M/descarga.png\" alt=\"descarga\">\n\nMaybe knowledge of breeds features, distribution of photos and visual analysis of pictures may help in this task of an image generation, delete the pictures with persons or 3 dogs ...\n**But**\n\n&gt; Imagenet pre-trained models are NOT allowed\n\ncheck: https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334",
      "votes": null
    },
    {
      "id": "564368",
      "postDate": "06/29/2019 10:39:25",
      "content": "<h1>New random pictures</h1>\n\n<p>This kind of pictures will make the work harder :(</p>\n\n<p>\n\n\n</p>",
      "rawMarkdown": "# New random pictures\n\nThis kind of pictures will make the work harder :(\n\n<img src=\"https://i.ibb.co/cxZ3nwd/Captura-de-pantalla-de-2019-06-29-12-31-41.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-41\">\n<img src=\"https://i.ibb.co/TRzg1JG/Captura-de-pantalla-de-2019-06-29-12-32-48.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-48\">\n<img src=\"https://i.ibb.co/LNgrSTj/Captura-de-pantalla-de-2019-06-29-12-32-28.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-28\">\n<img src=\"https://i.ibb.co/p1LBrz3/Captura-de-pantalla-de-2019-06-29-12-31-59.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-59\">",
      "votes": null
    },
    {
      "id": "564375",
      "postDate": "06/29/2019 10:51:14",
      "content": "<p>ty saitama</p>",
      "rawMarkdown": "ty saitama",
      "votes": null
    },
    {
      "id": "564503",
      "postDate": "06/29/2019 14:10:58",
      "content": "<p>Great analysis, Thanks for elaborating.</p>",
      "rawMarkdown": "Great analysis, Thanks for elaborating.",
      "votes": null
    },
    {
      "id": "564655",
      "postDate": "06/29/2019 18:41:03",
      "content": "<p>Great work. Also A+avatar.</p>",
      "rawMarkdown": "Great work. Also A+avatar.",
      "votes": null
    },
    {
      "id": "564673",
      "postDate": "06/29/2019 19:31:17",
      "content": "<p>Nice work. Lots thanks for sharing </p>",
      "rawMarkdown": "Nice work. Lots thanks for sharing",
      "votes": null
    },
    {
      "id": "569377",
      "postDate": "07/06/2019 14:51:25",
      "content": "<p>Thank you <a href=\"/jesucristo\">@jesucristo</a> </p>",
      "rawMarkdown": "Thank you @jesucristo",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 564368,
      "author_name": "jesucristo",
      "author_url": "",
      "post_date": "06/29/2019 10:39:25",
      "content": "<h1>New random pictures</h1>\n\n<p>This kind of pictures will make the work harder :(</p>\n\n<p>\n\n\n</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 564375,
      "author_name": "iluvmahheart",
      "author_url": "",
      "post_date": "06/29/2019 10:51:14",
      "content": "<p>ty saitama</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 564503,
      "author_name": "gunishj",
      "author_url": "",
      "post_date": "06/29/2019 14:10:58",
      "content": "<p>Great analysis, Thanks for elaborating.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 564655,
      "author_name": "investigatorbear",
      "author_url": "",
      "post_date": "06/29/2019 18:41:03",
      "content": "<p>Great work. Also A+avatar.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 564673,
      "author_name": "dataraj",
      "author_url": "",
      "post_date": "06/29/2019 19:31:17",
      "content": "<p>Nice work. Lots thanks for sharing </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 569377,
      "author_name": "joelhanson",
      "author_url": "",
      "post_date": "07/06/2019 14:51:25",
      "content": "<p>Thank you <a href=\"/jesucristo\">@jesucristo</a> </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "564347": "Thanks to [Vitaliy](@witold1) and his kernel [Quick data explanation and EDA](https://www.kaggle.com/witold1/quick-data-explanation-and-eda)\n\n### [Stanford Dogs Dataset](http://vision.stanford.edu/aditya86/ImageNetDogs/)\n\nThe Stanford Dogs dataset contains images of **120 breeds** of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. Contents of this dataset:\n\n- Number of categories: 120\n- Number of images: 20,580\n- Annotations: Class labels, Bounding boxes\n\nWe have  20579 pictures\n\n### Interesting data facts are\n\n- There are pictures with more than one dog (even with  **3  dogs**);\n- There are pictures with the dog (-s) and person (people);\n- There are pictures with more than one person (even with  **4  people**);\n- There are pictures where dogs occupy less than  1/5  of the picture;\n- There are pictures with text (magazine covers, from dog shows, memes and pictures with text);\n- Even wild predators included, e.g. African wild dog or Dingo, but not wolves.\n\n### Examples\n\n<img src=\"https://i.ibb.co/1ZytPCk/results-6-1.png\" alt=\"results-6-1\">\n<img src=\"https://i.ibb.co/rdv6Q9M/descarga.png\" alt=\"descarga\">\n\nMaybe knowledge of breeds features, distribution of photos and visual analysis of pictures may help in this task of an image generation, delete the pictures with persons or 3 dogs ...\n**But**\n\n&gt; Imagenet pre-trained models are NOT allowed\n\ncheck: https://www.kaggle.com/c/generative-dog-images/discussion/97751#latest-564334",
    "564368": "# New random pictures\n\nThis kind of pictures will make the work harder :(\n\n<img src=\"https://i.ibb.co/cxZ3nwd/Captura-de-pantalla-de-2019-06-29-12-31-41.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-41\">\n<img src=\"https://i.ibb.co/TRzg1JG/Captura-de-pantalla-de-2019-06-29-12-32-48.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-48\">\n<img src=\"https://i.ibb.co/LNgrSTj/Captura-de-pantalla-de-2019-06-29-12-32-28.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-28\">\n<img src=\"https://i.ibb.co/p1LBrz3/Captura-de-pantalla-de-2019-06-29-12-31-59.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-59\">",
    "564375": "ty saitama",
    "564503": "Great analysis, Thanks for elaborating.",
    "564655": "Great work. Also A+avatar.",
    "564673": "Nice work. Lots thanks for sharing",
    "569377": "Thank you @jesucristo"
  },
  "source": "meta"
}