{
  "id": 266955,
  "title": "My quick experiment",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/266955",
  "author_name": "",
  "post_date": "2021-08-21T04:16:23.945135400Z",
  "votes": 3,
  "comment_count": 3,
  "views": 0,
  "content": "<p>My quick experiment of using <a href=\"https://www.kaggle.com/thedrcat/g2net-train-images-with-gpwy-sample\" target=\"_blank\">this dataset</a> for training. I did this to have a quick experiment to learn about signal processing using images. The training notebook is <a href=\"https://www.kaggle.com/sapal6/g2gwd-base-model-fastai-resnet\" target=\"_blank\">here</a>.</p>\n<p>I didn't get a good LB score though but Learned a lot of things while doing this experiment(I never knew that deep learning on time series data can be done using time series as images.) </p>\n<p>Any suggestion on approaches which can be experimented with to increase the performance ?</p>\n<p>Also, I found that training on the entire dataset vs training only on a subset of 20,000 images yields similar performance while using resnet34.</p>",
  "messages": [
    {
      "id": "1484086",
      "postDate": "08/21/2021 04:16:23",
      "content": "<p>My quick experiment of using <a href=\"https://www.kaggle.com/thedrcat/g2net-train-images-with-gpwy-sample\" target=\"_blank\">this dataset</a> for training. I did this to have a quick experiment to learn about signal processing using images. The training notebook is <a href=\"https://www.kaggle.com/sapal6/g2gwd-base-model-fastai-resnet\" target=\"_blank\">here</a>.</p>\n<p>I didn't get a good LB score though but Learned a lot of things while doing this experiment(I never knew that deep learning on time series data can be done using time series as images.) </p>\n<p>Any suggestion on approaches which can be experimented with to increase the performance ?</p>\n<p>Also, I found that training on the entire dataset vs training only on a subset of 20,000 images yields similar performance while using resnet34.</p>",
      "rawMarkdown": "My quick experiment of using [this dataset](https://www.kaggle.com/thedrcat/g2net-train-images-with-gpwy-sample) for training. I did this to have a quick experiment to learn about signal processing using images. The training notebook is [here](https://www.kaggle.com/sapal6/g2gwd-base-model-fastai-resnet).\n\nI didn't get a good LB score though but Learned a lot of things while doing this experiment(I never knew that deep learning on time series data can be done using time series as images.) \n\nAny suggestion on approaches which can be experimented with to increase the performance ?\n\nAlso, I found that training on the entire dataset vs training only on a subset of 20,000 images yields similar performance while using resnet34.",
      "votes": null
    },
    {
      "id": "1486332",
      "postDate": "08/22/2021 21:53:31",
      "content": "<p>Thank you for sharing</p>",
      "rawMarkdown": "Thank you for sharing",
      "votes": null
    },
    {
      "id": "1486657",
      "postDate": "08/23/2021 06:19:58",
      "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> My pleasure.</p>",
      "rawMarkdown": "authman My pleasure.",
      "votes": null
    },
    {
      "id": "1561183",
      "postDate": "10/27/2021 12:15:18",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1486332,
      "author_name": "authman",
      "author_url": "",
      "post_date": "08/22/2021 21:53:31",
      "content": "<p>Thank you for sharing</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1486657,
      "author_name": "sapal6",
      "author_url": "",
      "post_date": "08/23/2021 06:19:58",
      "content": "<p><a href=\"https://www.kaggle.com/authman\" target=\"_blank\">@authman</a> My pleasure.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1561183,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 12:15:18",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1484086": "My quick experiment of using [this dataset](https://www.kaggle.com/thedrcat/g2net-train-images-with-gpwy-sample) for training. I did this to have a quick experiment to learn about signal processing using images. The training notebook is [here](https://www.kaggle.com/sapal6/g2gwd-base-model-fastai-resnet).\n\nI didn't get a good LB score though but Learned a lot of things while doing this experiment(I never knew that deep learning on time series data can be done using time series as images.) \n\nAny suggestion on approaches which can be experimented with to increase the performance ?\n\nAlso, I found that training on the entire dataset vs training only on a subset of 20,000 images yields similar performance while using resnet34.",
    "1486332": "Thank you for sharing",
    "1486657": "authman My pleasure.",
    "1561183": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}