{
  "fetched_at": "2026-10-20T07:28:08Z",
  "source_url": "https://www.kaggle.com/competitions/fungi-challenge-fgvc-2018/data",
  "pages": [
    {
      "name": "rules",
      "content": "- Pre-trained models are allowed in the competition (see Guidelines below).\n- Acquiring additional image or video data for the species in this competition is not allowed, either is using older versions of the dataset.\n- Participants are allowed to collect additional annotations (e.g. bounding boxes, keypoints) on the provided training and validation sets. Teams should specify that they collected additional annotations when submitting final results.\n- This competition does not count towards Kaggle ranking points or medals.\n- We ask that you respect the spirit of the competition and do not cheat. Hand-labeling is forbidden.\n\n<!-- Begin Base Rules -->\n<h3>One account per participant</h3>\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n\n<h3>No private sharing outside teams</h3>\n<p>Privately sharing code or data outside of teams is not permitted.\n       It's okay to share code if made available to all participants on the forums.</p>\n\n<h3>Guidelines</h3>\n<p>The general rule is that participants should only use the provided training and validation images to train a model to classify the test images. We do not want participants crawling the web in search of additional data. Pretrained models may be used to construct the algorithms (e.g. ImageNet pretrained models). Please specify any and all external data used for training when uploading results.</p>\n\n<h3>Terms of Use</h3>\n\nBy downloading this dataset you agree to the following terms:\n\n<ol>\n<li>You will use the data only for non-commercial research and educational purposes.</li>\n<li>You will NOT distribute the above images.</li>\n<li>The Danish Svampe Atlas makes no representations or warranties regarding the data, including but not limited to warranties of non-infringement or fitness for a particular purpose.</li>\n<li>You accept full responsibility for your use of the data and shall defend and indemnify the Danish Svampe Atlas, including its employees, officers and agents, against any and all claims arising from your use of the data, including but not limited to your use of any copies of copyrighted images that you may create from the data.</li>\n</ol>\n\n<h3>Team Mergers</h3>\n<p>\n   Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.\n</p>\n\n<h3>Team Limits</h3>\n<p>There is no maximum team size.</p>\n\n<h3>Submission Limits</h3>\n<p>You may submit a maximum of 5 entries per day.</p>\n<p>You may select up to 2 final submissions for judging.</p>\n\n<h3>Competition Timeline</h3>\n<p>Merger Deadline: <strong>June 4, 2018</strong></p>\n<p>Entry Deadline: <strong>June 4, 2018</strong></p>\n<p>End Date: <strong>June 11, 2018 11:59 PM UTC</strong></p>\n<!-- End Base Rules -->\n\n<h3>COMPETITION-SPECIFIC TERMS</h3>\n<h3>Competition Sponsors</h3>\nCompetition Name (the 'Competition'): FGVCx Fungi Classification Challenge at FGVC5\n\nCompetition Sponsors: FGVC5 Workshop and Svampe Atlas\n\nCompetition Acknowledgements: Brigit Schroeder, Yin Cui\n\nCompetition Website: https://www.kaggle.com/c/fungi-challenge-fgvc-2018 and https://sites.google.com/corp/view/fgvc5/home\n\nCompetitions are open to residents of the United States and worldwide, except if you are a resident of Crimea, Cuba, Iran, Syria, North Korea, Sudan, or are subject to U.S. export controls or sanctions, then you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions.\n\n<strong>ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.</strong>\n\n<p>The Competition named above is a skills-based competition to promote and further the field of data science. You must register via the Competition Website to enter. Your competition submissions (“Submissions”) must conform to the requirements set forth on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes described on the Competition Website, if any, will be awarded to participants with the best scores, based on the merits of the data science models submitted.</p>\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>Data</h2>\nDownload the images and annotations [here](https://github.com/visipedia/fgvcx_fungi_comp#data).\n<h2>File Descriptions</h2>\n<ul>\n<li><strong>fungi_train_val.tgz</strong> - The training and validation images in a directory structure following `images/category/image.jpg`</li>\n<li><strong>fungi_test.tgz</strong> - The testing images in a single directory `test/`</li>\n<li><strong>train_val_annotations.tgz</strong> - Contains training and validation annotations.</li>\n<li><strong>test_information.tgz</strong> - Contains testing image information.</li>\n<li><strong>fungi_sample_submission.csv</strong> - A sample submission file in the correct format.</li>\n</ul>\n<h2>Image Format</h2>\n<p>All images have been saved in the JPEG format and have been resized to have a maximum dimension of 1024 pixels.</p>\n\n<h2>Annotation Format</h2>\n\nWe closely follow the annotation format of the [COCO dataset][2]. The annotations are stored in the [JSON][3] format and are organized as follows:\n<pre>\n{\n  \"info\" : info,\n  \"images\" : [image],\n  \"categories\" : [category],\n  \"annotations\" : [annotation],\n  \"licenses\" : [license]\n}\n\ninfo{\n  \"year\" : int,\n  \"version\" : str,\n  \"description\" : str,\n  \"contributor\" : str,\n  \"url\" : str,\n  \"date_created\" : datetime,\n}\n\nimage{\n  \"id\" : int,\n  \"width\" : int,\n  \"height\" : int,\n  \"file_name\" : str,\n  \"license\" : int,\n  \"rights_holder\" : str\n}\n\ncategory{\n  \"id\" : int,\n  \"name\" : str,\n  \"supercategory\" : str,\n}\n\nannotation{\n  \"id\" : int,\n  \"image_id\" : int,\n  \"category_id\" : int\n}\n\nlicense{\n  \"id\" : int,\n  \"name\" : str,\n  \"url\" : str\n}`\n</pre>\n\n  [2]: http://cocodataset.org/#download\n  [3]: http://www.json.org/",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "![fungi cover image][1]\n\nThis 2018 Fungi Classification is an FGVCx competition as part of the [FGVC5][3] workshop at CVPR 2018. Our sponsor, the [Danish Svampe Atlas][2], has provided a dataset from a carefully curated database containing over 100,000 fungi images. The Svampe Atlas has  a comprehensive representation of nearly 1,500 wild mushrooms species which have been spotted and photographed by the general public in Denmark.\n\n\n\n  [1]: https://raw.githubusercontent.com/visipedia/fgvcx_fungi_comp/master/assets/fungi_cover_sm.jpg\n  [2]: https://svampe.databasen.org/\n  [3]: https://sites.google.com/view/fgvc5/home",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p> We follow a similar metric to the classification tasks of the ILSVRC. For each image, an algorithm will produce 3 labels. For this competition each image has one ground truth label. For a given image, if the ground truth label is found among the 3 predicted labels, then the error for that image is 0, otherwise it is 1. The final score is the error averaged across all images. See <a href=\"https://github.com/visipedia/fgvcx_fungi_comp#evaluation\">here</a> for additional information.\n\n<h2>Submission Format</h2>\n<p>For each image in the test set, you must predict 3 class labels. The csv file should contain a header and have the following format:</p>\n\n<pre>id,predicted<br />12345, 6 27 88<br />67890, 0 100 17<br/></pre>\n<p>The <b>id</b> column corresponds to the test image id. The <b>predicted</b> column corresponds to 3 category ids, separated by spaces. You should have one row for each test image. Please sort your predictions from most confident to least, from left to right, this will allow us to study top-1, top-2, and top-3 accuracy.</p>\n\n\n  [1]: https://github.com/visipedia/fgvcx_fungi_comp#evaluation",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "CVPR 2018",
      "content": "This competition is part of the <a href=\"https://sites.google.com/view/fgvc5/\">FGVC5</a> workshop at <a href=\"http://cvpr2018.thecvf.com/\">CVPR 2018</a>. Top submissions for the competition will be invited to give talks at the workshop. Attending the workshop is not required to participate in the competition, however only teams that are attending the workshop will be considered to present their work.\n\nThere is no cash prize for this competition. Attendees presenting in person are responsible for all costs associated with travel, expenses, and fees to attend CVPR 2018.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "- **June 4, 2018** - Entry deadline. You must accept the competition rules before this date in order to compete.\n- **June 4, 2018** - Team Merger deadline. This is the last day participants may join or merge teams.\n- **June 11, 2018** - Final submission deadline.\nAll deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}