{
  "fetched_at": "2026-10-19T07:16:10Z",
  "source_url": "https://www.kaggle.com/competitions/ammi-2021-convnets/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The data consists of two folders, a training folder that contains 5 subfolders that contain the respective images for the different 5 classes and a test folder containing test images.\n\nParticipants are to train their models using the images in the training folder and provide a submission file like the sample provided which contains the image name exactly matching the image name in the test folder and the corresponding class prediction with labels corresponding to the disease categories, cmd, healthy, cgm, cbsd, cbb.\n\nPlease cite this paper if you use the dataset for your project: https://arxiv.org/pdf/1908.02900.pdf\n\n## Folder descriptions\n- `train` - the set of training images for 5 categories of disease\n- `train/cbb` - the set of training images for class cbb\n- `train/cmd` - the set of training images for class cmd\n- `train/cbsd` - the set of training images for class cbsd\n- `train/cgm` - the set of training images for class cgm\n- `train/healthy` - the set of training images for class healthy\n- `test` - the set of test images to run your trained model on\n-  `extraimages.zip` - zip file with 12,595 unlabeled images of cassava leaves that participants can use as additional training data\n\n## File descriptions\n- `sampleSubmission.csv` - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "As the 2nd largest provider of carbohydrates in Africa, cassava is a key food security crop grown by small-holder farmers because it can withstand harsh conditions. At least 80% of small-holder farmer households in Sub-Saharan Africa grow cassava and viral diseases are major sources of poor yields.\n\nIn this competition, we introduce a dataset of 5 fine-grained cassava leaf disease categories with 9,436 labeled images collected during a regular survey in Uganda, mostly crowdsourced from farmers taking images of their gardens, and annotated by experts at the National Crops Resources Research Institute (NaCRRI) in collaboration with the AI lab in Makarere University, Kampala.\n\nThe dataset consists of leaf images of the cassava plant, with 9,436 annotated images and 12,595 unlabeled images of cassava leaves. Participants can choose to use the unlabeled images as additional training data. The goal is to learn a model to classify a given image into these 4 disease categories or a 5th category indicating a healthy leaf, using the images in the training data (participants can choose to use the unlabeled images in their training data). This competition is part of the fine-grained visual-categorization workshop (FGVC6 workshop) at CVPR 2019.\n\n<h2>Acknowledgements</h2>\nWe thank the different experts and collaborators from NaCRRI for assisting in preparing this dataset.\n\nWe thank Ernest Mwebaze, Timnit Gebru, Andrea Frome, Solomon Nsumba, Jeremy Tusubira, and Chris Omongo for developing the original version of this challenge.\n\n<h2>Citation</h2>\nPlease cite this paper if you use the dataset for your project: https://arxiv.org/pdf/1908.02900.pdf",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated based on the mean (top-1) accuracy metric on the test predictions. We assume that a prediction is correct if the top prediction is the ground-truth label. Please see our Github page for more details.\n\n<h2>Submission File Format</h2>\nimage_name, label\n\ntest_0001.jpg,0\n\ntest_0002.jpg,1\n\ntest_0003.jpg,3\n\nPlease include the header as shown above for correct parsing. Each line will correspond to one test image and will be identified by the id (e.g test0001.jpg refers to image test0001.jpg) for computing accuracy.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "The rules for this project are simple:\n\n - Don't cheat!\n - Have fun!\n\nAt the end of the project, write up a one-page report that describes the techniques you tried and the results you obtained. In grading the course, we care more about your report than about where you end up on the leaderboard.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}