{
  "fetched_at": "2026-10-20T09:02:37Z",
  "source_url": "https://www.kaggle.com/competitions/110-1-ai-edge-computing-hw1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This competition use the Fashion MNIST dataset created by Zalando Research. \nhttps://www.kaggle.com/zalando-research/fashionmnist\n\nThe dataset has been uploaded to Kaggle. Add the dataset directly in your Kaggle notebook. We upload the example file of prediction results here.\n\n## File\n\n*   **pred_results.csv** - Each row contains the sample ID (0 ~ 9999) and the predicted class ID.\n\n## Columns\n\n*   `Id` -  A test image's ID\n*   `Category` - Predicted class ID\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this homework we will use Fashion MNIST to train our first neural network model. The dataset set has been uploaded to Kaggle ( https://www.kaggle.com/zalando-research/fashionmnist ). \n\nPlease read the code in the example notebook \nhttps://www.kaggle.com/kuantinglai/notebook03880db6e1\nCreate your own notebook, design a model, train the model and make prediction on test data. Upload the prediction results of the test data. This is a multi-class classification problem and we use accuracy as the metric.\n\nIn order to identify the student’s account, please create an account name starting with your student ID.\n同學們的Kaggle帳號請用學號當帳號名稱開頭, 以便登記分數時辨識.\n\n## Acknowledgements\n\nWe thank Zalando Research for providing this dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Please do the homework by yourself and do not use test data as training data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}