{
  "fetched_at": "2026-10-20T10:30:25Z",
  "source_url": "https://www.kaggle.com/competitions/ai-at-mit-and-weights-biases-blood-mnist-2023/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset is in the Colab Notebook. You should use the Colab Notebook to generate a `submission.csv` file which you submit over here in Kaggle.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Competition details\n\nThe details of this competition will be shared in a separate resource.\n\nThe BloodMNIST dataset is part of the wider MedMNIST dataset.\n\nMedMNIST is a large-scale MNIST-like collection of standardized biomedical images, including twelve 2D datasets and six 3D datasets. All the images are pre-processed to the size of 28x28 pixels and working with the data requires no prior domain knowledge about medicine, genetics, biology, etc.\n\n## BloodMNIST details\n\nThe BloodMNIST is based on a dataset of individual normal cells, captured from individuals without infection, hematologic or oncologic disease and free of any pharmacologic treatment at the moment of blood collection. It contains a total of 17,092 images and is organized into 8 classes (8 different classes of blood cell).\n\n\n## Spoiler\n\nIf you'd like *a* solution to the proposed classification task we've included one that was authored by our colleagues Justin and Ayush here: [Integrating Keras with Weights and Biases](https://wandb.ai/ayush-thakur/medmnist-bloodmnist/reports/Integrating-Keras-with-Weights-Biases--VmlldzoxNDg1MDQy?utm_source=webinar&utm_medium=online&utm_campaign=windsor).\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "We'll be evaluating your prediction based on accuracy.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Contest rules:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}