{
  "id": 150981,
  "title": "Hierarchical Multi label image classification (CNN )",
  "url": "/competitions/dogs-vs-cats-redux-kernels-edition/discussion/150981",
  "author_name": "Guilherme",
  "post_date": "2020-05-14T01:54:10.125000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I would like to know if there is any example available that show how to create a model that combines two classification levels:\n1 - Is a dog or a cat ?\n2- If is a dog, what Dog breed ?  If is a cat, what cat breed ? </p>\n\n<p>I have found just examples using multi-class classification (not considering hierarchy):</p>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2008341%2Facbad2ccd13955b802e4378b1524c1ee%2Fkeras_multi_label_dataset.jpg?generation=1589420916983958&amp;alt=media\" alt=\"multi-class\"></p>\n\n<p>In this case, both features can happen (all clothes can have all colors). However, my case is different because the dog breed is different from cat breed. So the first label will define the second.</p>\n\n<p>If someone can help me, I would be very thankful.</p>",
  "messages": [
    {
      "id": 846754,
      "postDate": "2020-05-14T01:54:10.127Z",
      "content": "<p>I would like to know if there is any example available that show how to create a model that combines two classification levels:\n1 - Is a dog or a cat ?\n2- If is a dog, what Dog breed ?  If is a cat, what cat breed ? </p>\n\n<p>I have found just examples using multi-class classification (not considering hierarchy):</p>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2008341%2Facbad2ccd13955b802e4378b1524c1ee%2Fkeras_multi_label_dataset.jpg?generation=1589420916983958&amp;alt=media\" alt=\"multi-class\"></p>\n\n<p>In this case, both features can happen (all clothes can have all colors). However, my case is different because the dog breed is different from cat breed. So the first label will define the second.</p>\n\n<p>If someone can help me, I would be very thankful.</p>",
      "rawMarkdown": "I would like to know if there is any example available that show how to create a model that combines two classification levels:\n1 - Is a dog or a cat ?\n2- If is a dog, what Dog breed ?  If is a cat, what cat breed ? \n\nI have found just examples using multi-class classification (not considering hierarchy):\n\n\n![multi-class](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2008341%2Facbad2ccd13955b802e4378b1524c1ee%2Fkeras_multi_label_dataset.jpg?generation=1589420916983958&amp;alt=media)\n\nIn this case, both features can happen (all clothes can have all colors). However, my case is different because the dog breed is different from cat breed. So the first label will define the second.\n\nIf someone can help me, I would be very thankful.\n",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "846754": "I would like to know if there is any example available that show how to create a model that combines two classification levels:\n1 - Is a dog or a cat ?\n2- If is a dog, what Dog breed ?  If is a cat, what cat breed ? \n\nI have found just examples using multi-class classification (not considering hierarchy):\n\n\n![multi-class](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2008341%2Facbad2ccd13955b802e4378b1524c1ee%2Fkeras_multi_label_dataset.jpg?generation=1589420916983958&amp;alt=media)\n\nIn this case, both features can happen (all clothes can have all colors). However, my case is different because the dog breed is different from cat breed. So the first label will define the second.\n\nIf someone can help me, I would be very thankful.\n"
  }
}