{
  "id": 156386,
  "title": " [TF.Keras] Melanoma Starter (GPU)",
  "url": "/competitions/siim-isic-melanoma-classification/discussion/156386",
  "author_name": "",
  "post_date": "2020-06-05T18:47:23.872166600Z",
  "votes": 6,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi, \nThere's a plethora example notebook for modeling melanoma classifiers in <strong>TPU</strong> with <code>tf</code>. Here, I like to share a starter scripts modeling in <strong>GPU</strong>. </p>\n\n<ul>\n<li><a href=\"https://www.kaggle.com/ipythonx/tf-keras-melanoma-classification-starter-gpu?scriptVersionId=35534415\">[TF.Keras] Melanoma Classification Starter : GPU</a></li>\n</ul>\n\n<p>I've trained <code>EfficientNet B0</code> with just 3 epochs on 224 resized samples. I hope you find it useful. Thank you :)</p>",
  "messages": [
    {
      "id": "875404",
      "postDate": "06/05/2020 18:47:23",
      "content": "<p>Hi, \nThere's a plethora example notebook for modeling melanoma classifiers in <strong>TPU</strong> with <code>tf</code>. Here, I like to share a starter scripts modeling in <strong>GPU</strong>. </p>\n\n<ul>\n<li><a href=\"https://www.kaggle.com/ipythonx/tf-keras-melanoma-classification-starter-gpu?scriptVersionId=35534415\">[TF.Keras] Melanoma Classification Starter : GPU</a></li>\n</ul>\n\n<p>I've trained <code>EfficientNet B0</code> with just 3 epochs on 224 resized samples. I hope you find it useful. Thank you :)</p>",
      "rawMarkdown": "Hi, \nThere's a plethora example notebook for modeling melanoma classifiers in **TPU** with `tf`. Here, I like to share a starter scripts modeling in **GPU**. \n\n- [[TF.Keras] Melanoma Classification Starter : GPU](https://www.kaggle.com/ipythonx/tf-keras-melanoma-classification-starter-gpu?scriptVersionId=35534415)\n\nI've trained `EfficientNet B0` with just 3 epochs on 224 resized samples. I hope you find it useful. Thank you :)",
      "votes": null
    },
    {
      "id": "875429",
      "postDate": "06/05/2020 19:15:08",
      "content": "<p>Fantastic notebook. Well organized, clean pipeline, great explanations! This is a great resource for everyone. Thank you</p>",
      "rawMarkdown": "Fantastic notebook. Well organized, clean pipeline, great explanations! This is a great resource for everyone. Thank you",
      "votes": null
    },
    {
      "id": "875477",
      "postDate": "06/05/2020 20:14:01",
      "content": "<p>Thank you <a href=\"/cdeotte\">@cdeotte</a> 😀 </p>",
      "rawMarkdown": "Thank you @cdeotte 😀",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 875429,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "06/05/2020 19:15:08",
      "content": "<p>Fantastic notebook. Well organized, clean pipeline, great explanations! This is a great resource for everyone. Thank you</p>",
      "votes": null,
      "replies": [
        {
          "id": 875477,
          "author_name": "ipythonx",
          "author_url": "",
          "post_date": "06/05/2020 20:14:01",
          "content": "<p>Thank you <a href=\"/cdeotte\">@cdeotte</a> 😀 </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "875404": "Hi, \nThere's a plethora example notebook for modeling melanoma classifiers in **TPU** with `tf`. Here, I like to share a starter scripts modeling in **GPU**. \n\n- [[TF.Keras] Melanoma Classification Starter : GPU](https://www.kaggle.com/ipythonx/tf-keras-melanoma-classification-starter-gpu?scriptVersionId=35534415)\n\nI've trained `EfficientNet B0` with just 3 epochs on 224 resized samples. I hope you find it useful. Thank you :)",
    "875429": "Fantastic notebook. Well organized, clean pipeline, great explanations! This is a great resource for everyone. Thank you",
    "875477": "Thank you @cdeotte 😀"
  },
  "source": "meta"
}