{
  "fetched_at": "2026-10-24T17:43:28Z",
  "source_url": "https://www.kaggle.com/competitions/109-2-ntut-dl-app-hw2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In Homework 2 we are going to train models that can recommend hashtags based on the content of an image. We will use the dataset \"HARRISON\". Please refer to the paper (https://arxiv.org/abs/1605.05054) for more details about the dataset.\n\nThe original data of HARRISON can be downloaded here: https://drive.google.com/file/d/1B9NZf42J_GpslRNlTTAxvM5c9WRVl_1Z/view?usp=sharing. \n\nYou can download the images and take a look, but this is not mandatory. We already extracted the image features, compressed them as \"harrison_features.npz\", and upload to Kaggle:\nhttps://www.kaggle.com/kuantinglai/harrison-dataset\n\n\nThe training process is split into two stages: hashtag2vec training and image-to-word2vec training. Please refer to the notebook of this competition. The steps are\n1. Run https://www.kaggle.com/kuantinglai/train-htag2vec-tf1\n2. Download \"tag\\_list\\_word2vec\\_64.npz\" (The number 64 may be changed, it depends on your vector dimension)\n3. Run https://www.kaggle.com/kuantinglai/train-devise-w-ur-htag2vec, upload your  \"tag\\_list\\_word2vec\\_64.npz\"\n4. Download \"harrison\\_test\\_predict.csv\" and submit\n\nTo evaluate the model performance, we use the mean Average Precision (mAP) @ 10. Enjoy the homework and Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "We use mean Average Precision (mAP) to evaluate the performance. Please refer to \nhttps://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Average_precision\nOr \nhttps://darren1231.pixnet.net/blog/post/347752732-machine-learning-map%28mean-average-precision%29-%E8%A9%B3%E7%B4%B0%E8%A7%A3%E8%AA%AA\n\nfor detailed explanation of Average Precision.",
      "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
    }
  ]
}