{
  "id": 49909,
  "title": "[LB 0.407] submit and notebook with visualizations",
  "url": "/competitions/data-science-bowl-2018/discussion/49909",
  "author_name": "kamil",
  "post_date": "2018-02-16T16:52:34.711000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>Recently, we published <a href=\"https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb\">devbook.ipynb</a> on our Open Solution repository.</p>\n\n<p>We did some training of the Multi-output U-Net, which learns mask, contour, and center. We put all our predictions available on-line via <a href=\"https://neptune.ml/\">neptune.ml</a>.</p>\n\n<p>Our <a href=\"https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb\">devbook.ipynb</a> let's you visualize and browse these predictions -&gt; we think that it is convenient way to gain intuition about what your network generates.</p>\n\n<p>You can also generate Kaggle submit on these predictions and easily get <code>[LB 0.407]</code>.</p>\n\n<p>You can use it via <a href=\"https://neptune.ml/\">neptune.ml</a> -&gt; notebook is ready to go.</p>\n\n<p>Best,</p>\n\n<p>Kamil</p>",
  "messages": [
    {
      "id": 284140,
      "postDate": "2018-02-16T16:52:34.710Z",
      "content": "<p>Hi,</p>\n\n<p>Recently, we published <a href=\"https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb\">devbook.ipynb</a> on our Open Solution repository.</p>\n\n<p>We did some training of the Multi-output U-Net, which learns mask, contour, and center. We put all our predictions available on-line via <a href=\"https://neptune.ml/\">neptune.ml</a>.</p>\n\n<p>Our <a href=\"https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb\">devbook.ipynb</a> let's you visualize and browse these predictions -&gt; we think that it is convenient way to gain intuition about what your network generates.</p>\n\n<p>You can also generate Kaggle submit on these predictions and easily get <code>[LB 0.407]</code>.</p>\n\n<p>You can use it via <a href=\"https://neptune.ml/\">neptune.ml</a> -&gt; notebook is ready to go.</p>\n\n<p>Best,</p>\n\n<p>Kamil</p>",
      "rawMarkdown": "Hi,\n\nRecently, we published [devbook.ipynb](https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb) on our Open Solution repository.\n\nWe did some training of the Multi-output U-Net, which learns mask, contour, and center. We put all our predictions available on-line via [neptune.ml](https://neptune.ml).\n\nOur [devbook.ipynb](https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb) let's you visualize and browse these predictions -&gt; we think that it is convenient way to gain intuition about what your network generates.\n\nYou can also generate Kaggle submit on these predictions and easily get `[LB 0.407]`.\n\nYou can use it via [neptune.ml](https://neptune.ml) -&gt; notebook is ready to go.\n\nBest,\n\nKamil\n",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "284140": "Hi,\n\nRecently, we published [devbook.ipynb](https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb) on our Open Solution repository.\n\nWe did some training of the Multi-output U-Net, which learns mask, contour, and center. We put all our predictions available on-line via [neptune.ml](https://neptune.ml).\n\nOur [devbook.ipynb](https://github.com/neptune-ml/data-science-bowl-2018/blob/master/devbook.ipynb) let's you visualize and browse these predictions -&gt; we think that it is convenient way to gain intuition about what your network generates.\n\nYou can also generate Kaggle submit on these predictions and easily get `[LB 0.407]`.\n\nYou can use it via [neptune.ml](https://neptune.ml) -&gt; notebook is ready to go.\n\nBest,\n\nKamil\n"
  }
}