{
  "id": 99496,
  "title": " data augmentation",
  "url": "/competitions/aptos2019-blindness-detection/discussion/99496",
  "author_name": "",
  "post_date": "2019-07-11T18:27:35.359128300Z",
  "votes": 2,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Hi everyone,\nPlease, suggest me which data augmentation technique i can try on these kind of images. </p>",
  "messages": [
    {
      "id": "573057",
      "postDate": "07/11/2019 18:27:35",
      "content": "<p>Hi everyone,\nPlease, suggest me which data augmentation technique i can try on these kind of images. </p>",
      "rawMarkdown": "Hi everyone,\nPlease, suggest me which data augmentation technique i can try on these kind of images.",
      "votes": null
    },
    {
      "id": "573152",
      "postDate": "07/11/2019 21:22:46",
      "content": "<p>You can look for various data augmentation techniques in public kernels. For instance, here: <a href=\"https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model\">https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model</a>\nI would suggest albumentations library: <a href=\"https://github.com/albu/albumentations\">https://github.com/albu/albumentations</a> It has many transforms, good tutorials and it is pretty fast</p>",
      "rawMarkdown": "You can look for various data augmentation techniques in public kernels. For instance, here: https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model\nI would suggest albumentations library: https://github.com/albu/albumentations It has many transforms, good tutorials and it is pretty fast",
      "votes": null
    },
    {
      "id": "573382",
      "postDate": "07/12/2019 07:37:31",
      "content": "<p>I illustrate 6 sensible data augmentation with visualization by Grad CAM<a href=\"https://www.kaggle.com/ratthachat/aptos-updated-albumentation-meets-grad-cam/\"> <strong>here in this kernel</strong></a>. Hope it is helpful.</p>\n\n<p><img src=\"https://i.ibb.co/H4MJWVz/gradcam-album.png\" alt=\"Albumentation meets Grad-CAM\"></p>",
      "rawMarkdown": "I illustrate 6 sensible data augmentation with visualization by Grad CAM[ **here in this kernel**](https://www.kaggle.com/ratthachat/aptos-updated-albumentation-meets-grad-cam/). Hope it is helpful.\n\n![Albumentation meets Grad-CAM](https://i.ibb.co/H4MJWVz/gradcam-album.png)",
      "votes": null
    },
    {
      "id": "573411",
      "postDate": "07/12/2019 08:39:06",
      "content": "<p><a href=\"/blackitten13\">@blackitten13</a> this look pretty useful. will try this.. thanks</p>",
      "rawMarkdown": "blackitten13 this look pretty useful. will try this.. thanks",
      "votes": null
    },
    {
      "id": "573412",
      "postDate": "07/12/2019 08:40:02",
      "content": "<p><a href=\"/ratthachat\">@ratthachat</a>  thanks for sharing the kernel.. will check ..</p>",
      "rawMarkdown": "ratthachat  thanks for sharing the kernel.. will check ..",
      "votes": null
    },
    {
      "id": "573922",
      "postDate": "07/13/2019 00:45:16",
      "content": "<p>Hi! <a href=\"/shwetai\">@shwetai</a>, I been trying to utilize a few ideas from this repo: <a href=\"https://github.com/aleju/imgaug\">https://github.com/aleju/imgaug</a></p>",
      "rawMarkdown": "Hi! @shwetai, I been trying to utilize a few ideas from this repo: https://github.com/aleju/imgaug",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 573152,
      "author_name": "blackitten13",
      "author_url": "",
      "post_date": "07/11/2019 21:22:46",
      "content": "<p>You can look for various data augmentation techniques in public kernels. For instance, here: <a href=\"https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model\">https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model</a>\nI would suggest albumentations library: <a href=\"https://github.com/albu/albumentations\">https://github.com/albu/albumentations</a> It has many transforms, good tutorials and it is pretty fast</p>",
      "votes": null,
      "replies": [
        {
          "id": 573411,
          "author_name": "shwetai",
          "author_url": "",
          "post_date": "07/12/2019 08:39:06",
          "content": "<p><a href=\"/blackitten13\">@blackitten13</a> this look pretty useful. will try this.. thanks</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 573382,
      "author_name": "ratthachat",
      "author_url": "",
      "post_date": "07/12/2019 07:37:31",
      "content": "<p>I illustrate 6 sensible data augmentation with visualization by Grad CAM<a href=\"https://www.kaggle.com/ratthachat/aptos-updated-albumentation-meets-grad-cam/\"> <strong>here in this kernel</strong></a>. Hope it is helpful.</p>\n\n<p><img src=\"https://i.ibb.co/H4MJWVz/gradcam-album.png\" alt=\"Albumentation meets Grad-CAM\"></p>",
      "votes": null,
      "replies": [
        {
          "id": 573412,
          "author_name": "shwetai",
          "author_url": "",
          "post_date": "07/12/2019 08:40:02",
          "content": "<p><a href=\"/ratthachat\">@ratthachat</a>  thanks for sharing the kernel.. will check ..</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 573922,
      "author_name": "cv13j0",
      "author_url": "",
      "post_date": "07/13/2019 00:45:16",
      "content": "<p>Hi! <a href=\"/shwetai\">@shwetai</a>, I been trying to utilize a few ideas from this repo: <a href=\"https://github.com/aleju/imgaug\">https://github.com/aleju/imgaug</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "573057": "Hi everyone,\nPlease, suggest me which data augmentation technique i can try on these kind of images.",
    "573152": "You can look for various data augmentation techniques in public kernels. For instance, here: https://www.kaggle.com/artgor/basic-eda-and-baseline-pytorch-model\nI would suggest albumentations library: https://github.com/albu/albumentations It has many transforms, good tutorials and it is pretty fast",
    "573382": "I illustrate 6 sensible data augmentation with visualization by Grad CAM[ **here in this kernel**](https://www.kaggle.com/ratthachat/aptos-updated-albumentation-meets-grad-cam/). Hope it is helpful.\n\n![Albumentation meets Grad-CAM](https://i.ibb.co/H4MJWVz/gradcam-album.png)",
    "573411": "blackitten13 this look pretty useful. will try this.. thanks",
    "573412": "ratthachat  thanks for sharing the kernel.. will check ..",
    "573922": "Hi! @shwetai, I been trying to utilize a few ideas from this repo: https://github.com/aleju/imgaug"
  },
  "source": "meta"
}