{
  "fetched_at": "2026-10-24T04:41:26Z",
  "source_url": "https://www.kaggle.com/competitions/assignment2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Use the file paths in the .csv to read the images.\n使用各類型資料所屬的csv中的路徑，進行檔案的讀取。\n\n**Files**\n- fashion-mnist_train.csv - the training set\n- fashion-mnist_val.csv - the validation set\n\n**Columns**\n- label - the label of the image\n- pixel - the pixels of the image of shape 28 * 28",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this assignment is Accuracy metric. Submission Format For every image in the dataset, submission files should contain 2 columns: id and category.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Don't cheat!\n- Apply yourself!\n- Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "NSYSU MIS Deep Learning Assignment2 Competition\n- Please go to Team page and change your team name to your student ID. Ex. M114020035\n\n- Goal：Predict the category of fashion items: ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot'.]\n\n- How to do：Please write a classification model, train you model with the training data and predict the categories with the testing data. Finally, upload your prediction to Kaggle.\n\n- Assignment score evaluation：\n    - Accuracy of your prediction\n- Note：The accuracy score shown on your Kaggle leaderboard is only 70% of the test data, the final score will be shown after the competition is over, which will be the accuracy of the whole test data。\n\n- 請先至上方 Team 頁面將隊伍名稱改成學號。Ex. M114020035\n\n- 目標：預測時尚單品的種類 ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot'.]\n作業進行方式：請同學寫一個分類的模型，利用 training data 訓練後，進行 testing data 預測，並將預測結果上傳到Kaggle\n\n- 分數衡量方式：\n\n    - 預測準確度\n- 注意：Kaggle顯示的 Public leaderboard 為預測結果中70%資料的準確度，最終成績為所有資料的準確度。",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}