{
  "fetched_at": "2026-10-19T08:27:05Z",
  "source_url": "https://www.kaggle.com/competitions/extracting-attributes-from-fashion-images-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "All the training images are uploaded in the train folder with prefix Image and the respective class labels have been mapped in train_label.csv. In train_label.csv, we have normalized the target classes to 0-6(7 classes in total).\nYou'll be predicting the class of each image in the test folder and submitting the data in the csv format shown in sample_submission.csv.\n\n## Files\n\n*   **train.csv** - the training set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `file_name` - Name of the image\n*   `label` - Real class label of the image.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Goal of the competition:**\n\nThe competition aims to accurately identify/extract the trouser fit type from fashion apparel trousers images. Participants will make predictions on a diverse set of fashion images. \n\n**Context:**\n\nAttributes are important characteristics of the fashion products that define their uniqueness. For instance, long sleeve length and round collar are two attributes (among many) that characterize shirts. Likewise there are numerous attributes defining a certain product and the uniqueness associated with it. \n\nExtracting relevant attributes from fashion images is crucial to driving user demand and preferences and solving fashion-related problems.\n\n**Challenges**\nThe data is tagged internally and has class imbalance. The accuracy of the tags aren't ideal and have few errors (noise). The problem requires participants to come up with efficient training strategies to overcome these challenges.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on Categorization Accuracy between the predicted class and the tagged target.\n\n## Submission Format\n\nFor each submission, the submission file should contain the file name and the predicted class by the model for the respective image. The accuracy will be calculated based on the predicted class.\n\nThe file should contain a header and have the following format:\n\n```\n| file_name            |  label|\n| Image_test_000000.jpg|      0|\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Pretrained models and data from other open-source datasets can be used.\n- We ask that you respect the spirit of the competition and do not cheat.\n\n**No private sharing**\nNo sharing of the data.\n\n**One account per participant**\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n**No teaming**\nYou shouldn't team up and should participate the competition individually.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}