{
  "fetched_at": "2026-10-19T15:01:46Z",
  "source_url": "https://www.kaggle.com/competitions/cnn-hands-on-practice/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Context\n\nThe whole world is suffering from COVID-19 disease and its proper and timely diagnosis is the need of the hour. So for building an efficient AI-based diagnostic system we have collected Chest ray images from different sources so that we can train our CNN model for automating the whole diagnosis method. Therefore we have collected Chest ray images from different sources and research papers and combined them to create one comprehensive dataset that can be used by research community.\n\nThis dataset is also used in COVID Lite paper which has shown significant results by building novel CNN based solution.\n\n## Content\n\nThis dataset consists of a posteroanterior (PA) view of chest X-ray images comprising Normal, Viral, and CVOID-19 affected patients. There are total 1823 CXR images.\n\n## Acknowledgements\n\nPlease cite these papers if you are using it for any scientific purpose:\n\n1. D. Kermany, K. Zhang, M. Goldbaum, Large dataset of labeled optical coherence tomography (oct) and chest x-ray images, Mendeley Data, v3 http://dx. doi. org/10.17632/rscbjbr9sj 3 (2018).\n2. C. J. P, P. Morrison, D. L, Covid-19 image data collection, arxiv, arXiv preprint arXiv:2003.11597 (2020). URL https://github.com/ieee8023/covid-chestxray-dataset\n3. Z.-H. Chen, Mask-rcnn detection of covid-19 pneumonia symptoms by employing stacked autoencoders in deep unsupervised learning on low-dose\n    high resolution ct (2020). doi:10.21227/4kcm-m312.URL http://dx.doi.org/10.21227/4kcm-m312\n4. D. S. et.al, Covid19action-radiology-cxr (2020). doi:10.21227/s7pw-jr18.\n    URL http://dx.doi.org/10.21227/s7pw-jr18\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "In this hands-on practice session, we will focus on building, training, and evaluating a Convolutional Neural Network (CNN) for image classification. CNNs are a class of deep learning models widely used for analyzing visual data. They are designed to automatically and adaptively learn spatial hierarchies of features from input images, making them highly effective for tasks such as image recognition, object detection, and segmentation.\n\nOur objective is to apply a CNN model to classify a dataset of images into three categories: COVID, normal, and virus. The dataset consists of labeled images stored in separate directories, and we will use TensorFlow and Keras libraries to implement the CNN. The process involves several steps, including data preprocessing, model building, training, evaluation, and generating predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}