{
  "fetched_at": "2026-10-24T16:05:14Z",
  "source_url": "https://www.kaggle.com/competitions/flower-classification/data",
  "pages": [
    {
      "name": "data-description",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "題目類型<\\br>\n本資料為花朵資料集，總共有100個類別左右的花朵。<\\br>\n所有花朵圖片都集中放置在images資料夾內，標籤資料為train.csv、valid.csv。<\\br>\ntest.csv是我們欲預測的目標。<\\br>\n\n練習方向<\\br>\nData preprocessing and data augmentation<\\br>\nCNN model construction and hyper-parameter tuning<\\br>\nTransfer Learning<\\br>\n\n**Metrics **<\\br>\nAccuracy<\\br>\n\n\n\n上傳次數<\\br>\n一天可以上傳20次，選出您覺得最好的5個當作最後成績。 上傳時，Team Name請確認好命名<\\br>\n\n紀錄點<\\br>\n將於05/14/2020, 00:00 紀錄成績作為參考。<\\br>\n\n\nCategorical Accuracy: It evaluates the index of the maximal true value is equal to the index of the maximal predicted value. you need to specify your target (y) as label encoded vector (e.g. in case of 102 classes, when a true class is a second class, y should be 1.<\\br>\n\n通過條件<\\br>\n超越 Public baseline ( level1 or level2 )<\\br>\n\nbaseline_2.csv<\\br>\n\t\n\t0.90926<\\br>\n\nbaseline_1.csv<\\br>\n\t\n\t0.85073<\\br>\n",
      "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
    }
  ]
}