{
  "id": 202304,
  "title": "[TF.Keras]: Advanced Augmentations in Sequence Generator ",
  "url": "/competitions/cassava-leaf-disease-classification/discussion/202304",
  "author_name": "Innat",
  "post_date": "2020-12-09T10:23:10.156000",
  "votes": 7,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Hey guys, <br>\nWe're sharing a kernel that will show how you can use state-of-the-art augmentation such as <code>CutMix</code>, <code>MixUp</code>, and <code>FMix</code> in your custom data generator in <code>tf.keras</code>.  I found it rare and pesky to integrate before but now here it is. -) </p>\n<ul>\n<li><a href=\"https://www.kaggle.com/ipythonx/tf-keras-sota-augmentation-in-sequence-generator/notebook?scriptVersionId=48892220\" target=\"_blank\">SOTA Augmentation in Sequence Generator</a></li>\n</ul>",
  "messages": [
    {
      "id": 1107036,
      "postDate": "2020-12-09T10:23:10.157Z",
      "content": "<p>Hey guys, <br>\nWe're sharing a kernel that will show how you can use state-of-the-art augmentation such as <code>CutMix</code>, <code>MixUp</code>, and <code>FMix</code> in your custom data generator in <code>tf.keras</code>.  I found it rare and pesky to integrate before but now here it is. -) </p>\n<ul>\n<li><a href=\"https://www.kaggle.com/ipythonx/tf-keras-sota-augmentation-in-sequence-generator/notebook?scriptVersionId=48892220\" target=\"_blank\">SOTA Augmentation in Sequence Generator</a></li>\n</ul>",
      "rawMarkdown": "Hey guys, \nWe're sharing a kernel that will show how you can use state-of-the-art augmentation such as `CutMix`, `MixUp`, and `FMix` in your custom data generator in `tf.keras`.  I found it rare and pesky to integrate before but now here it is. -) \n\n- [SOTA Augmentation in Sequence Generator](https://www.kaggle.com/ipythonx/tf-keras-sota-augmentation-in-sequence-generator/notebook?scriptVersionId=48892220)\n",
      "votes": 7
    },
    {
      "id": 1108653,
      "postDate": "2020-12-10T21:28:59.630Z",
      "content": "<p>Is there a simpler resource from which I can understand these augmentations in layman terms. That would be really helpful!</p>",
      "rawMarkdown": "Is there a simpler resource from which I can understand these augmentations in layman terms. That would be really helpful!",
      "votes": 1,
      "replies": [
        {
          "id": 1109008,
          "postDate": "2020-12-11T08:39:40.870Z",
          "rawMarkdown": "",
          "isDeleted": true
        }
      ]
    },
    {
      "id": 1107163,
      "postDate": "2020-12-09T13:00:54.193Z",
      "content": "<p>Thank you, now augmentations are more informative with your kernel.</p>",
      "rawMarkdown": "Thank you, now augmentations are more informative with your kernel."
    }
  ],
  "comments": [
    {
      "id": 1108653,
      "author_name": "Rahul Tiwari",
      "author_url": "",
      "post_date": "2020-12-10T21:28:59.630000",
      "content": "<p>Is there a simpler resource from which I can understand these augmentations in layman terms. That would be really helpful!</p>",
      "votes": 1,
      "replies": [
        {
          "id": 1109008,
          "author_name": "",
          "author_url": "",
          "post_date": "2020-12-11T08:39:40.870000",
          "content": "",
          "votes": 0,
          "replies": []
        }
      ]
    },
    {
      "id": 1107163,
      "author_name": "",
      "author_url": "",
      "post_date": "2020-12-09T13:00:54.193000",
      "content": "<p>Thank you, now augmentations are more informative with your kernel.</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1107036": "Hey guys, \nWe're sharing a kernel that will show how you can use state-of-the-art augmentation such as `CutMix`, `MixUp`, and `FMix` in your custom data generator in `tf.keras`.  I found it rare and pesky to integrate before but now here it is. -) \n\n- [SOTA Augmentation in Sequence Generator](https://www.kaggle.com/ipythonx/tf-keras-sota-augmentation-in-sequence-generator/notebook?scriptVersionId=48892220)\n",
    "1108653": "Is there a simpler resource from which I can understand these augmentations in layman terms. That would be really helpful!",
    "1107163": "Thank you, now augmentations are more informative with your kernel."
  }
}