{
  "fetched_at": "2026-10-19T06:28:01Z",
  "source_url": "https://www.kaggle.com/competitions/d-4-computer-vision/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Plant disease detection via computer vision could be a very important to protecting the agriculture industry. This dataset contains 4235 images of healthy and/or diseased leaves. Within this dataset, there are 10 different plant species with a variety of leaf shapes and degrees of disease progression. There are 3 csv files: train, test, and sample_submission. The train file has one column being the image (with the image_id) and the other being the label (0: healthy and 1: for diseased), the test file only having the image column (no answers).\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `Images` - JPG image id\n*   `Labels` - 0: healthy and 1: diseased\n\n## Data Source\nDataset modified from the \"Healthy vs. Diseased Leaf Image Dataset\" (License CC0: Public domain) on Kaggle at https://www.kaggle.com/datasets/amandam1/healthy-vs-diseased-leaf-image-dataset ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this lab, you will design a CNN that can detect diseased or healthy plant leaves. \n\n**#Computer Vision****\n\"Computer vision is an area of machine learning dedicated to interpreting and understanding images and video. It is used to help teach computers to “see” and to use visual information to perform visual tasks that humans can.\" (https://www.run.ai/guides/deep-learning-for-computer-vision#:~:text=Computer%20vision%20algorithms%20analyze%20certain,commonly%20used%20for%20computer%20vision.) \n\nThe link above is a great source to learn more about computer vision and how the CNN behind it work.\n\n# **Code Example of CNN Model**\n\\```model = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(300, 150, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\\```\n\n# **Instructions**\n1. Load and look through the data\n2. I suggest some potential image augmentation, this is a large dataset\n3. Design a CNN that is able to accurately detect diseased and healthy leaves (Example above)\n- Try and find parameters that will give the best accuracy \n4. Look at sample submission on what you submission should look like ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "This lab will be graded on accuracy, the percentage of times the model is able to correctly identify diseased and healthy leaves. \n\n---\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n         Images        Labels\n    1  0011_0100.JPG    0\n    2  0009_0053.JPG    1\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Rules for this challenges:\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n - Plants are the ultimate organism!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is a project on using Computer Vision for the D4 program.\n\n\n**Goal:** Using computer vision CNN to detect healthy vs diseased plant leaves.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}