{
  "fetched_at": "2026-10-19T10:03:24Z",
  "source_url": "https://www.kaggle.com/competitions/bitmoji-faces-gender-recognition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This is the documentation describing the dataset usage.\nFirst, there are 3000 labeled datasets in the train images folder, which are divided by themselves.\nThere are 1084 images in the test mages folder. You need to predict the gender and keypoint coordinates of the images and save them to a csv file.\nWhen submitting, only the val.csv file needs to be submitted.\nscore:\nFor 1084 pieces, we divided into two lists, the public list and the private list. The private rankings will be released the day after the competition ends.\nThe highest score on both lists is 1.00\n\n## Files\n\n*   **train.csv** - the train images data labels \n*   **sample_submission.csv** - a sample submission file in the correct format\n提交只需要对数据集 属性进行二分类,按照 样例csv格式提交\n\n\n## Columns\n\n*   image_id    :    image  id string\n*   is_male      :   -1 or 1  \n\nFor details, please see sample_submission.csv。\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Bitmoji Faces Gender Recognition\nBitmoji cartoon faces, with 5-point facial landmarks and the gender of faces.\n\n## Acknowledgements\n\nWe thank Professor Mostafa Mozafari, Ph.D. for providing this dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top; the page title appears above. For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have included below:\n\n---\n\nThe evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\nupload test.csv\n\nThe file should contain a header and have the following format:\n```\nimage_id\tis_male left_eye_x left_eye_y\t right_eye_x right_eye_y\t nose_x nose_y mouth_left_x mouth_left_y mouth_right_x mouth_right_y\n3000.jpg\t 1\t152\t186\t236\t183\t196\t234\t158\t262\t231\t260\n3001.jpg \n3002.jpg\n'''\nnotice:  \"\tis_male \" is 1 or -1  Other evaluation data is of type double\n\n``` ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\nYou can discuss methods with each other, but don't copy.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}