{
  "id": 162152,
  "title": "Resized Jpg Dataset : train + external dataset",
  "url": "/competitions/siim-isic-melanoma-classification/discussion/162152",
  "author_name": "",
  "post_date": "2020-06-27T16:09:33.239428600Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>I have resized in jpg format using opencv for people who plan to use pytorch as I haven't find any topic about that, excepted the one of Chris Deotte for tensorflow (TFrecord). (128x128 256x256, 512x512 , 768x768)\nIt can be usefull for people with small gpu at home for instance.</p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg768768\">https://www.kaggle.com/ludovick/melanomaresizedjpg768768</a>\n<a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg512\">https://www.kaggle.com/ludovick/melanomaresizedjpg512</a></p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg\">https://www.kaggle.com/ludovick/melanomaresizedjpg</a>\nupdate : external dataset, thanks to this notebook : <a href=\"https://www.kaggle.com/shonenkov/merge-external-data\">https://www.kaggle.com/shonenkov/merge-external-data</a></p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanoma-external-jpg\">https://www.kaggle.com/ludovick/melanoma-external-jpg</a></p>",
  "messages": [
    {
      "id": "904432",
      "postDate": "06/27/2020 16:09:33",
      "content": "<p>Hi,</p>\n\n<p>I have resized in jpg format using opencv for people who plan to use pytorch as I haven't find any topic about that, excepted the one of Chris Deotte for tensorflow (TFrecord). (128x128 256x256, 512x512 , 768x768)\nIt can be usefull for people with small gpu at home for instance.</p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg768768\">https://www.kaggle.com/ludovick/melanomaresizedjpg768768</a>\n<a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg512\">https://www.kaggle.com/ludovick/melanomaresizedjpg512</a></p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanomaresizedjpg\">https://www.kaggle.com/ludovick/melanomaresizedjpg</a>\nupdate : external dataset, thanks to this notebook : <a href=\"https://www.kaggle.com/shonenkov/merge-external-data\">https://www.kaggle.com/shonenkov/merge-external-data</a></p>\n\n<p><a href=\"https://www.kaggle.com/ludovick/melanoma-external-jpg\">https://www.kaggle.com/ludovick/melanoma-external-jpg</a></p>",
      "rawMarkdown": "Hi,\n\nI have resized in jpg format using opencv for people who plan to use pytorch as I haven't find any topic about that, excepted the one of Chris Deotte for tensorflow (TFrecord). (128x128 256x256, 512x512 , 768x768)\nIt can be usefull for people with small gpu at home for instance.\n\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg768768\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg512\n\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg\nupdate : external dataset, thanks to this notebook : https://www.kaggle.com/shonenkov/merge-external-data\n\nhttps://www.kaggle.com/ludovick/melanoma-external-jpg",
      "votes": null
    },
    {
      "id": "904435",
      "postDate": "06/27/2020 16:13:29",
      "content": "<p>I've not used this myself, but there is this handy tool that allows PyTorch to ingest TFRecords very easily: <a href=\"https://github.com/vahidk/tfrecord\">https://github.com/vahidk/tfrecord</a></p>",
      "rawMarkdown": "I've not used this myself, but there is this handy tool that allows PyTorch to ingest TFRecords very easily: https://github.com/vahidk/tfrecord",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 904435,
      "author_name": "anjum48",
      "author_url": "",
      "post_date": "06/27/2020 16:13:29",
      "content": "<p>I've not used this myself, but there is this handy tool that allows PyTorch to ingest TFRecords very easily: <a href=\"https://github.com/vahidk/tfrecord\">https://github.com/vahidk/tfrecord</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "904432": "Hi,\n\nI have resized in jpg format using opencv for people who plan to use pytorch as I haven't find any topic about that, excepted the one of Chris Deotte for tensorflow (TFrecord). (128x128 256x256, 512x512 , 768x768)\nIt can be usefull for people with small gpu at home for instance.\n\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg768768\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg512\n\nhttps://www.kaggle.com/ludovick/melanomaresizedjpg\nupdate : external dataset, thanks to this notebook : https://www.kaggle.com/shonenkov/merge-external-data\n\nhttps://www.kaggle.com/ludovick/melanoma-external-jpg",
    "904435": "I've not used this myself, but there is this handy tool that allows PyTorch to ingest TFRecords very easily: https://github.com/vahidk/tfrecord"
  },
  "source": "meta"
}