{
  "id": 205173,
  "title": "Someone has published a very interesting work: Multi-Attention EfficientNet",
  "url": "/competitions/ranzcr-clip-catheter-line-classification/discussion/205173",
  "author_name": "",
  "post_date": "2020-12-18T19:57:46.489650600Z",
  "votes": 12,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Every competition works with interesting approaches are buried because they don't has a score. I found the work <a href=\"https://www.kaggle.com/ipythonx/tf-keras-ranzcr-multi-attention-efficientnet\" target=\"_blank\">[TF.Keras]: RANZCR: Multi-Attention EfficientNet</a> made by <a href=\"https://www.kaggle.com/ipythonx\" target=\"_blank\">M.Innat</a>. Maybe he is going to publish a <em>discussion</em> soon so, i'm not going to write more. Upvote his work is you find as interesting as i do.</p>",
  "messages": [
    {
      "id": "1118183",
      "postDate": "12/18/2020 19:57:46",
      "content": "<p>Every competition works with interesting approaches are buried because they don't has a score. I found the work <a href=\"https://www.kaggle.com/ipythonx/tf-keras-ranzcr-multi-attention-efficientnet\" target=\"_blank\">[TF.Keras]: RANZCR: Multi-Attention EfficientNet</a> made by <a href=\"https://www.kaggle.com/ipythonx\" target=\"_blank\">M.Innat</a>. Maybe he is going to publish a <em>discussion</em> soon so, i'm not going to write more. Upvote his work is you find as interesting as i do.</p>",
      "rawMarkdown": "Every competition works with interesting approaches are buried because they don't has a score. I found the work [[TF.Keras]: RANZCR: Multi-Attention EfficientNet](https://www.kaggle.com/ipythonx/tf-keras-ranzcr-multi-attention-efficientnet) made by [M.Innat](https://www.kaggle.com/ipythonx). Maybe he is going to publish a *discussion* soon so, i'm not going to write more. Upvote his work is you find as interesting as i do.",
      "votes": null
    },
    {
      "id": "1122331",
      "postDate": "12/22/2020 11:03:44",
      "content": "<p>Thanks for bringing it up here. However, I may not publish any discussion for now but will integrate some stuff soon in the notebook. -)</p>",
      "rawMarkdown": "Thanks for bringing it up here. However, I may not publish any discussion for now but will integrate some stuff soon in the notebook. -)",
      "votes": null
    },
    {
      "id": "1122465",
      "postDate": "12/22/2020 13:06:07",
      "content": "<p>I'm going to follow your posts, i like the way that you implement papers with <strong>tensorflow 2.x</strong>.</p>",
      "rawMarkdown": "I'm going to follow your posts, i like the way that you implement papers with **tensorflow 2.x**.",
      "votes": null
    },
    {
      "id": "1124755",
      "postDate": "12/24/2020 07:22:47",
      "content": "<p>This is really interesting ! <a href=\"https://www.kaggle.com/hiramcho\" target=\"_blank\">@hiramcho</a> </p>",
      "rawMarkdown": "This is really interesting ! @hiramcho",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1122331,
      "author_name": "ipythonx",
      "author_url": "",
      "post_date": "12/22/2020 11:03:44",
      "content": "<p>Thanks for bringing it up here. However, I may not publish any discussion for now but will integrate some stuff soon in the notebook. -)</p>",
      "votes": null,
      "replies": [
        {
          "id": 1122465,
          "author_name": "hiramcho",
          "author_url": "",
          "post_date": "12/22/2020 13:06:07",
          "content": "<p>I'm going to follow your posts, i like the way that you implement papers with <strong>tensorflow 2.x</strong>.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1124755,
      "author_name": "saurabhshahane",
      "author_url": "",
      "post_date": "12/24/2020 07:22:47",
      "content": "<p>This is really interesting ! <a href=\"https://www.kaggle.com/hiramcho\" target=\"_blank\">@hiramcho</a> </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1118183": "Every competition works with interesting approaches are buried because they don't has a score. I found the work [[TF.Keras]: RANZCR: Multi-Attention EfficientNet](https://www.kaggle.com/ipythonx/tf-keras-ranzcr-multi-attention-efficientnet) made by [M.Innat](https://www.kaggle.com/ipythonx). Maybe he is going to publish a *discussion* soon so, i'm not going to write more. Upvote his work is you find as interesting as i do.",
    "1122331": "Thanks for bringing it up here. However, I may not publish any discussion for now but will integrate some stuff soon in the notebook. -)",
    "1122465": "I'm going to follow your posts, i like the way that you implement papers with **tensorflow 2.x**.",
    "1124755": "This is really interesting ! @hiramcho"
  },
  "source": "meta"
}