{
  "id": 158404,
  "title": "Guide to Fine tuning and Feature extraction with Keras",
  "url": "/competitions/dogs-vs-cats-redux-kernels-edition/discussion/158404",
  "author_name": "",
  "post_date": "2020-06-14T08:24:20.825703900Z",
  "votes": 1,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Dear fellow Kagglers,</p>\n\n<p>I have just shared a notebook that illustrates how we can build our own custom CNN. The notebook also make use of pre-trained models like (VGG16, ResNet) for fine-tuning,  and as feature extractor (pass convolved feature maps into Logistic regression).\nHope you can take a look and it and any feedbacks will be much appreciated!</p>\n\n<p>Notebook link: <a href=\"https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/\">https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/</a>?</p>\n\n<p>Thank you:)</p>",
  "messages": [
    {
      "id": "885458",
      "postDate": "06/14/2020 08:24:20",
      "content": "<p>Dear fellow Kagglers,</p>\n\n<p>I have just shared a notebook that illustrates how we can build our own custom CNN. The notebook also make use of pre-trained models like (VGG16, ResNet) for fine-tuning,  and as feature extractor (pass convolved feature maps into Logistic regression).\nHope you can take a look and it and any feedbacks will be much appreciated!</p>\n\n<p>Notebook link: <a href=\"https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/\">https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/</a>?</p>\n\n<p>Thank you:)</p>",
      "rawMarkdown": "Dear fellow Kagglers,\n\nI have just shared a notebook that illustrates how we can build our own custom CNN. The notebook also make use of pre-trained models like (VGG16, ResNet) for fine-tuning,  and as feature extractor (pass convolved feature maps into Logistic regression).\nHope you can take a look and it and any feedbacks will be much appreciated!\n\nNotebook link: https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/?\n\nThank you:)",
      "votes": null
    },
    {
      "id": "885567",
      "postDate": "06/14/2020 10:19:19",
      "content": "<p>Thanks for sharing. I see an error in the final predict code block though. Thanks.</p>",
      "rawMarkdown": "Thanks for sharing. I see an error in the final predict code block though. Thanks.",
      "votes": null
    },
    {
      "id": "885631",
      "postDate": "06/14/2020 11:00:16",
      "content": "<p>Hi, yes there was error as the notebook i created wasnt meant for any submission, just as a guide for transfer learning :) Will update it according!</p>",
      "rawMarkdown": "Hi, yes there was error as the notebook i created wasnt meant for any submission, just as a guide for transfer learning :) Will update it according!",
      "votes": null
    },
    {
      "id": "885758",
      "postDate": "06/14/2020 13:10:08",
      "content": "<p>Gotcha. Good notebook by the way. Upvoted.</p>",
      "rawMarkdown": "Gotcha. Good notebook by the way. Upvoted.",
      "votes": null
    },
    {
      "id": "885820",
      "postDate": "06/14/2020 13:58:09",
      "content": "<p>thank you very much :)</p>",
      "rawMarkdown": "thank you very much :)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 885567,
      "author_name": "binaicrai",
      "author_url": "",
      "post_date": "06/14/2020 10:19:19",
      "content": "<p>Thanks for sharing. I see an error in the final predict code block though. Thanks.</p>",
      "votes": null,
      "replies": [
        {
          "id": 885631,
          "author_name": "angqx95",
          "author_url": "",
          "post_date": "06/14/2020 11:00:16",
          "content": "<p>Hi, yes there was error as the notebook i created wasnt meant for any submission, just as a guide for transfer learning :) Will update it according!</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 885758,
          "author_name": "binaicrai",
          "author_url": "",
          "post_date": "06/14/2020 13:10:08",
          "content": "<p>Gotcha. Good notebook by the way. Upvoted.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 885820,
          "author_name": "angqx95",
          "author_url": "",
          "post_date": "06/14/2020 13:58:09",
          "content": "<p>thank you very much :)</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "885458": "Dear fellow Kagglers,\n\nI have just shared a notebook that illustrates how we can build our own custom CNN. The notebook also make use of pre-trained models like (VGG16, ResNet) for fine-tuning,  and as feature extractor (pass convolved feature maps into Logistic regression).\nHope you can take a look and it and any feedbacks will be much appreciated!\n\nNotebook link: https://www.kaggle.com/angqx95/feature-extractor-fine-tuning-with-keras/?\n\nThank you:)",
    "885567": "Thanks for sharing. I see an error in the final predict code block though. Thanks.",
    "885631": "Hi, yes there was error as the notebook i created wasnt meant for any submission, just as a guide for transfer learning :) Will update it according!",
    "885758": "Gotcha. Good notebook by the way. Upvoted.",
    "885820": "thank you very much :)"
  },
  "source": "meta"
}