{
  "fetched_at": "2026-10-25T01:01:12Z",
  "source_url": "https://www.kaggle.com/competitions/dialssl/data",
  "pages": [
    {
      "name": "data-description",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# 2021 DIAL / Image classification with Semi Supervised Learning\n\n![description_1](https://i.imgur.com/fl86beG.png)\n- Build a machine learning model for the image classification with few labeled data where most of the data are unlabeled. Leverage ‘large unlabeled data’ to improve the model performance which originally has ‘small sized labeled data’ only.\n\n\nReference :\nhttps://paperswithcode.com/task/semi-supervised-image-classification\nhttps://amitness.com/2020/07/semi-supervised-learning/\nhttps://blog.est.ai/2020/11/ssl/\n\n\n### 1. **Baseline(100%)**\nThe score results from trained model with 40,551 labeled dataset. (whole train dataset)\nModel : CNN in model.py file\n\nThe baseline uses hyper-parameters as below.\n![params](https://i.imgur.com/gewatbq.png)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}