{
  "fetched_at": "2026-10-24T03:22:34Z",
  "source_url": "https://www.kaggle.com/competitions/gan-getting-started/data",
  "pages": [
    {
      "name": "rules",
      "content": "### Getting Started Honor Code\n\nThis is a fun competition aimed at helping you get started with using TPUs in machine learning.  While it may be possible to artificially inflate your score by submitting images that were not truly generative, this defeats the entire purpose.  So seriously, don't do that.\n\n### One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### No private sharing outside teams\n\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n### Team Mergers\n\nTeam 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\n### Team Limits\n\nThe maximum team size is 5.\n\n### Submission Limits\n\nYou may submit a maximum of 5 entries per day.\n\nFinal submissions selection is not relevant for Getting Started competitions\n\n### Competition Timeline\n\nStart Date: August 28, 2020\n\nMerger Deadline: None\n\nEntry Deadline: None\n\nCompetition End Date: None\n\n### COMPETITION-SPECIFIC TERMS\n\n**COMPETITION TITLE**: I'm Something of a Painter Myself\n\n**COMPETITION SPONSOR**: Kaggle\n\n**COMPETITION WEBSITE**: https://www.kaggle.com/c/gan-getting-started\n\n**WINNER LICENSE TYPE**: None\n\n**DATA ACCESS AND USE**: Any purpose\n\nCompetitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea, or are subject to U.S. export controls or sanctions, 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. The Competition Host reserves the right to forego or award alternative Prizes where needed to comply with local laws. If a winner is located in a country where prizes cannot be awarded then they are not eligible to receive a prize.\n\n**ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.**\n\nThe 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 stated 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, if any, will be awarded to participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.\n\n### A. COMPETITION-SPECIFIC RULES\n\nIn addition to the provisions of the General Competition Rules below, you understand and agree to these Specific Competition Rules required by the Competition Sponsor:\n\nThis competition does not count towards Kaggle ranking points or medals.\n\n**SPONSOR AND HOSTING PLATFORM.**\n\nThe following provision supersedes General Rules Section 3 below: “The Competition is sponsored and hosted by Kaggle Inc. (“Kaggle”).  As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at < www.kaggle.com/terms > in addition to these Rules.\"\n\n**AUTOMATED MACHINE LEARNING TOOLS (AMLT).** \n\nThis competition permits the use of automated machine learning tool(s) (“AMLT”) in the creation of Submissions. \n \nIndividual participants and Teams may also use an AMLT (i.e. Google AutoML, H2O Driverless AI, etc.) to create a Submission, provided that the participant ensures that they have an appropriate license to the AMLT and are able to comply with the Rules. \n\n### B. GENERAL COMPETITION RULES\n#### **1.\tBINDING AGREEMENT.** \n\nTo enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules above (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that submission of an entry in the Competition constitutes agreement to these Rules. You may not submit an entry to the Competition and are not eligible to receive the prizes associated with this Competition (“Prizes”) unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition.\n\n#### **2.\tELIGIBILITY.** \n\nA. To be eligible to enter the Competition, you must be:\n\t(i) a registered account holder at Kaggle.com; \n\t(ii) the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); \n\t(iii) not a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and\n\t(iv) not a person or representative of an entity under U.S. export controls or sanctions (see [https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx][1]).\n\nIf you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and the entity you represent or are an employee. If you are acting within the scope of your employment, as an employee, contractor, or agent of another party, you warrant that such party has full knowledge of your actions and has consented thereto, including your potential receipt of a Prize. You further warrant that your actions do not violate your employer's or entity's policies and procedures.   \n\nThe Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.\n\nB. Unless otherwise stated in the Specific Competition Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.\n\n#### **3.\tSPONSOR AND HOSTING PLATFORM.** \n\nThe Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.\n\n#### **4.\tCOMPETITION PERIOD.** \n\nFor the purposes of Prizes, the Competition will run from the Start Date and time to the End Date and time (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. *YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.* \n\n#### **5.\tCOMPETITION ENTRY.** \n\nNO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\n\nSubmissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\n\nIf the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.\n\nSubmissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n\n#### **6.\tINDIVIDUALS AND TEAMS.** \n\nA. *Individual Account*. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. \n\nB. *Teams*. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a \"Team\"); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\n\nC. *Team Merger*. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \n\n#### **7.\tCOMPETITION DATA.** \n\n\"Competition Data\" means the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants. \n\nA. *Data Access and Use*. You may access and use the Competition Data for any purpose, whether commercial or non-commercial, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n \nThe Competition Data is also subject to the following terms and conditions of the WikiArt and Flickr licenses under which it was originally licensed: [WikiArt License](https://www.wikiart.org/) & [Flickr License](https://www.flickr.com/creativecommons/), as specified by the CycleGAN \"monet2photo\" dataset's published sources: [CycleGAN](https://github.com/junyanz/CycleGAN). To the extent that the terms and conditions located at the URL conflict with or are inconsistent with these Rules, these Rules will govern your use of the Competition Data.\n \nB. *Data Security*. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.\n\nC. *External Data*. You may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, you will ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants.\n\n#### **8.\tSUBMISSION CODE REQUIREMENTS.**\n\nA. *Private Code Sharing*. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\n\nB. *Public Code Sharing*. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or kernels associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\n\nC. *Use of Open Source*. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.\n\n#### **9.\tDETERMINING LEADERBOARD.** \n\nEach Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The public leaderboard will be based on the public test set and the private leaderboard will be based on the private test set.\n\nIn the event of a tie, the Submission that was entered first to the Competition will be ranked higher.\n\n#### **10.\tDISQUALIFICATION.**\n\nCompetition Sponsor reserves the right to disqualify any participant from the Competition if the Competition Sponsor reasonably believes that the participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other participants, Competition Sponsor or Kaggle.\n \nA disqualified participant may be removed from the Competition leaderboard, at Kaggle's sole discretion.\n \nThe final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n\n#### **11.\tGENERAL CONDITIONS.**\n\nAll federal, state, provincial and local laws and regulations apply.   \n\n#### **12.\tPUBLICITY.** \n\nYou agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.\n\n#### **13.\tPRIVACY.** \n\nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <www.kaggle.com/privacy>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <www.kaggle.com/contact>.\n \nAs part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n\n\n#### **14.\tWARRANTY, INDEMNITY AND RELEASE.**  \n\nYou warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses.  You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\n\nTo the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any prize, or your participation in the Competition and any Competition-related activity.\n\nYou hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; or (b) any error in the collection, processing, or retention of any Submission.\n\n\n#### **15.\tINTERNET.**\n\nCompetition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a participant’s ability to participate.\n\n#### **16.\tRIGHT TO CANCEL, MODIFY OR DISQUALIFY.**\n\nIf for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any participant who tampers with the submission process or any other part of the Competition or Competition Website.  Any attempt by a participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such participant to the fullest extent of the applicable law.\n\n#### **17.\tNOT AN OFFER OR CONTRACT OF EMPLOYMENT.** \n\nUnder no circumstances will the entry of a Submission or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n#### **18.\tGOVERNING LAW.** \n\nUnless otherwise provided in the Competition Specific Rules above, all claims arising out of or relating to these Rules will be governed by California law, excluding its conflict of laws rules, and will be litigated exclusively in the Federal or State courts of Santa Clara County, California, USA. The parties consent to personal jurisdiction in those courts. If any provision of these Rules is held to be invalid or unenforceable, all remaining provisions of the Rules will remain in full force and effect.\n\n\n  [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n  [2]: http://www.kaggle.com/terms\n  [3]: http://www.opensource.org\n  [4]: http://www.opensource.org\n  [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n  [6]: http://www.kaggle.com/privacy\n  [7]: http://www.kaggle.com/contact",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": ">*“Every artist dips his brush in his own soul, and paints his own nature into his pictures.”*\n-Henry Ward Beecher\n \nWe recognize the works of artists through their unique style, such as color choices or brush strokes. The “je ne sais quoi” of artists like Claude Monet can now be imitated with algorithms thanks to generative adversarial networks (GANs). In this getting started competition, you will bring that style to your photos or recreate the style from scratch!\n \nComputer vision has advanced tremendously in recent years and GANs are now capable of mimicking objects in a very convincing way.  But creating museum-worthy masterpieces is thought of to be, well, more art than science. So can (data) science, in the form of GANs, trick classifiers into believing you’ve created a true Monet? That’s the challenge you’ll take on!\n\n\n## The Challenge:\n \nA GAN consists of at least two neural networks: a generator model and a discriminator model. The generator is a neural network that creates the images. For our competition, you should generate images in the style of Monet. This generator is trained using a discriminator.\n \nThe two models will work against each other, with the generator trying to trick the discriminator, and the discriminator trying to accurately classify the real vs. generated images.\n \nYour task is to build a GAN that generates 7,000 to 10,000 Monet-style images. \n\n\n## Getting Started:\n \nDetails on the dataset can be found [here](https://www.kaggle.com/c/gan-getting-started/data) and an overview of the evaluation process can be found [here](https://www.kaggle.com/c/gan-getting-started/overview/evaluation).\n \nTo learn how to submit and answers to other FAQs, review the [Frequently Asked Questions](https://www.kaggle.com/c/gan-getting-started/overview/frequently-asked-questions).\n \n<div class=\"note\">\n<strong>Recommended Tutorial</strong><br>\nWe highly recommend <a href=\"https://www.kaggle.com/amyjang/monet-cyclegan-tutorial\">Amy Jang's notebook </a> that goes over the basics of loading data from TFRecords, using TPUs, and building a CycleGAN.\n</div>\n\nAlthough the competition dataset only includes Monet images, check out this [dataset](https://github.com/junyanz/CycleGAN) for Cezanne, Ukiyo-e, and Van Gogh paintings to run your GAN on.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## MiFID\n\nSubmissions are evaluated on MiFID (Memorization-informed Fréchet Inception Distance), which is a modification from [Fréchet Inception Distance (FID)](https://arxiv.org/abs/1706.08500). \n\nThe smaller MiFID is, the better your generated images are.  \n\n\n\n## What is FID?\nOriginally published [here](https://arxiv.org/abs/1706.08500) ([github](https://github.com/bioinf-jku/TTUR)), FID, along with [Inception Score (IS)](https://arxiv.org/abs/1606.03498), are both commonly used in recent publications as the standard for evaluation methods of GANs. \n\nIn FID, we use the Inception network to extract features from an intermediate layer. Then we model the data distribution for these features using a multivariate Gaussian distribution with mean µ and covariance Σ. The FID between the real images \\\\(r\\\\) and generated images \\\\(g\\\\) is computed as:\n\n\\\\[\n\\text{FID} = ||\\mu\\_r - \\mu\\_g||^2 + \\text{Tr} (\\Sigma\\_r + \\Sigma\\_g - 2 (\\Sigma\\_r \\Sigma\\_g)^{1/2})\n\\\\]\n\nwhere \\\\(Tr\\\\) sums up all the diagonal elements. FID is calculated by computing the Fréchet distance between two Gaussians fitted to feature representations of the Inception network.\n\n\n\n## What is MiFID (Memorization-informed FID)?\nIn addition to FID, Kaggle takes training sample memorization into account. \n\nThe memorization distance is defined as the minimum cosine distance of all training samples in the feature space, averaged across all user generated image samples. This distance is thresholded, and it's assigned to 1.0 if the distance exceeds a pre-defined epsilon. \n\nIn mathematical form:\n\n\\\\[d\\_{ij} = 1 - cos(f\\_{gi}, f\\_{rj}) = 1 - \\frac{f\\_{gi} \\cdot f\\_{rj}}{|f\\_{gi}| |f\\_{rj}|}\\\\] \n\nwhere \\\\(f\\_g\\\\) and \\\\(f\\_r\\\\) represent the generated/real images in feature space (defined in pre-trained networks); and \\\\(f\\_{gi}\\\\) and \\\\(f\\_{rj}\\\\) represent the \\\\(i^{th}\\\\) and \\\\(j^{th}\\\\) vectors of \\\\(f\\_g\\\\) and \\\\(f\\_r\\\\), respectively. \n\n\n\\\\[d = \\frac{1}{N} \\sum\\_{i} \\min\\_j d\\_{ij} \\\\]\n\ndefines the minimum distance of a certain generated image (\\\\(i\\\\)) across all real images ((\\\\(j\\\\)), then averaged across all the generated images. \n\n![enter image description here][1]\ndefines the threshold of the weight only applies when the (\\\\(d\\\\)) is below a certain empirically determined threshold. \n\nFinally, this memorization term is applied to the FID:\n\\\\[ MiFID = FID \\cdot \\frac{1}{d\\_{thr}}\\\\]\n\n## Kaggle's workflow calculating MiFID for public and private scores\nKaggle calculates public MiFID scores with the pre-train neural network [Inception](http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz), and the public images used for evaluation are the rest of the TFDS Monet paintings. **Note that as a Getting Started competition there is no private leaderboard.**\n\nA demo of our MiFID evaluation code can be seen [here](https://www.kaggle.com/wendykan/demo-mifid-metric-for-dog-image-generation-comp).\n\n\n## Submission File\nYou are going to generate 7,000-10,000 Monet-style images that are in `jpg` format. Their sizes should be 256x256x3 (RGB). Then you need to zip those images and your output from your Kernel should only have **ONE** output file named `images.zip`. \n\nPlease note that Kaggle Kernels has a number of output files capped at 500. We highly encourage you to either directly write to a `zip` file as you generate images, or create a folder at `../tmp` as your temporary directory. \n\n> **Honor Code**: This competition has a unique format with images expected as submission, rather than predictions. Competitors should be using **generative methods** to create their submission images and not directly submit images of Monet paintings or altered versions of such images. This defeats purpose of a getting started competition aimed at learning.\n\n\n  [1]: https://storage.googleapis.com/kaggle-media/competitions/GAN/latex-img-150.png\n  [2]: https://storage.googleapis.com/kaggle-media/competitions/GAN/Kaggle%20GAN%20Diagram%20(3).png",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The dataset contains four directories: `monet_tfrec`, `photo_tfrec`, `monet_jpg`, and `photo_jpg`. The `monet_tfrec` and `monet_jpg` directories contain the same painting images, and the `photo_tfrec` and `photo_jpg` directories contain the same photos.\n \nWe recommend using TFRecords as a Getting Started competition is a great way to become more familiar with a new data format, but JPEG images have also been provided.\n \nThe `monet` directories contain Monet paintings. Use these images to train your model.\n \nThe `photo` directories contain photos. Add Monet-style to these images and submit your generated jpeg images as a zip file. Other photos outside of this dataset can be transformed but keep your submission file limited to 10,000 images.\n \nNote: Monet-style art can be created from scratch using other GAN architectures like DCGAN. The submitted image files do not necessarily have to be transformed photos.\n \nCheck out [the CycleGAN dataset](https://github.com/junyanz/CycleGAN) to experiment with the artistic style of other artists.\n \n## Files\n\n*   **monet_jpg** - 300 Monet paintings sized 256x256 in JPEG format\n*   **monet_tfrec** - 300 Monet paintings sized 256x256 in TFRecord format\n*   **photo_jpg** - 7028 photos sized 256x256 in JPEG format\n*   **photo_tfrec** - 7028 photos sized 256x256 in TFRecord format\n\n## Submission format\n\nYour kernel's output must be called `images.zip` and contain 7,000-10,000 images sized 256x256.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Code Requirements",
      "content": "![Kerneler](https://storage.googleapis.com/kaggle-media/competitions/general/Kerneler-white-desc2_transparent.png)\n### This is a Code Competition\n\nSubmissions to this competition must be made by an output from a Kaggle Notebook/Script.\n\n- CPU Notebook <= 5 hours run-time\n- GPU Notebook <= 5 hours run-time\n- TPU Notebook <= 3 hours run-time\n- Enabling internet allowed\n- The submission file must be named `images.zip`, containing a zip file of 7,000-10,000 images sized 256x256. Review details on the [Data Page](https://www.kaggle.com/c/gan-getting-started/data).\n\nPlease see the [Code Competition FAQ](https://www.kaggle.com/docs/competitions#kernels-only-FAQ) for more information on how to submit.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Frequently Asked Questions",
      "content": "### How do I make a submission?\n\nIn this unique code competition, you are writing code in a Kaggle notebook that generates an `images.zip` file containing 7,000-10,000 images sized 256x256. To submit from a notebook, you should:\n\n 1. Click on \"New Notebook\" from either the [Competition's Notebooks Page](https://www.kaggle.com/c/gan-getting-started/notebooks) or \"Submit Predictions\" flow.\n \n 2. This will fire up a **Kaggle Notebook**, our cloud-hosted notebook/script platform. You must submit your code through this environment.\n\n 3. The \"Data\" page and notebook environment will contain the recommended external dataset to use (Monet paintings and Photos). You are welcome to bring in your own external data to experiment with!\n\n 4. Your notebook must run within the defined [Code Requirements](https://www.kaggle.com/c/gan-getting-started/overview/code-requirements) constraints.\n\n 5. Your notebook's output file must be named `images.zip` and contain 7,000-10,000 images sized 256x256. Also refer to the [Evaluation](https://www.kaggle.com/c/gan-getting-started/overview/evaluation) page for details of how the submission is evaluated.\n\n 6. **Commit** your kernel. Click \"Save Version\" on the Notebook and choose \"Save & Run All (Commit)\". It may take some time for the notebook to run, but you can close the browser while it runs and return to it later.\n\n 7. If the Commit is successful and your code has generated an `images.zip` file, it will be shown in the notebook's **Output** section while in notebook viewer mode.\n\n 8. To submit, choose \"Make A Submission\" from the right navigation of your committed notebook *or* click \"Submit\" from the noteboook's \"Output\". If an Output has been generated but submission is not available, then your kernel has enabled some setting that is not permitted per the [Code Requirements](https://www.kaggle.com/c/gan-getting-started/overview/code-requirements) page.\n\n 9. Your submission may take some time to process. Once it kicks off, you can close your browser and return to see your standing on the Public Leaderboard when it finishes! The submission will not re-run your original notebook. It will be running your `images.zip` file through the classifier that determines how well your generative images match the Monet style and serves as this competition's evaluation metric.\n\n### What is a Getting Started competition? \n\nGetting Started competitions were created by Kaggle data scientists for people who have little to no machine learning background. They are a great place to begin if you are new to data science or just finished a MOOC and want to get involved in Kaggle.\n\nGetting Started competitions are a non-competitive way to get familiar with Kaggle’s platform, learn basic machine learning concepts, and start meeting people in the community. They have no cash prize and are on a rolling timeline.\n\n### What’s the difference between a private and public leaderboard?\n\nIn this competition, because it is a Getting Started competition, there is no difference. And we will refresh the competition every three months, so the Private Leaderboard is irrelevant.\n\nFor non-Getting Started Kaggle competitions, there is the concept of a public and private leaderboard to prevent participants from “overfitting” to the leaderboard. If your model is “overfit” to a dataset then it is not generalizable outside of the dataset you trained it on. This means that your model would have low accuracy on another sample of data taken from a similar dataset.\n\n### How do I create and manage a team?\n\nWhen you accept the competition rules, a team will be created for you. You can invite others to your team, accept a merger with another team, and update basic information like team name by going to the [Team page](https://www.kaggle.com/c/gan-getting-started/team).\n\nWe've heard from many Kagglers that teaming up is the best way to learn new skills AND have fun. If you don't have a teammate already, consider asking if anyone wants to team up in the [discussion forum](https://www.kaggle.com/c/gan-getting-started/discussion).\n\n### What are Notebooks?\n\nKaggle Notebooks is a cloud computational environment that enables reproducible and collaborative analysis. Kernels supports scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the [Notebooks tab](https://www.kaggle.com/c/gan-getting-started/notebooks) to view all of the publicly shared code on this competition. For more on how to use Notebooks to learn data science, visit Kaggle's [Learn Courses](https://www.kaggle.com/learn/overview).\n\n### Why did my team disappear from the leaderboard?\n\nTo keep with the spirit of getting-started competitions, we have implemented a three month rolling window on submissions. Once a submission is more than three months old, it will be invalidated and no longer count towards the leaderboard.\n\nIf your team has no submissions in the previous three months, the team will also drop from the leaderboard. This will keep the leaderboard at a manageable size, freshen it up, and prevent newcomers from getting lost in a sea of abandoned scores.\n\n*\"I worked so hard to get that score! Give it back!\"* Read more about our decision to implement rolling leaderboards, covered in the [Titanic Getting Started Competition forum here](https://www.kaggle.com/c/titanic/discussion/6240).\n\n### How do I contact Support?\n\nKaggle does not have a dedicated support team so you’ll typically find that you receive a response more quickly by asking your question in the appropriate forum. (For this competition, you’ll want to use [this competition's discussion forum](https://www.kaggle.com/c/gan-getting-started/discussion).\n\nSupport is only able to help with issues that are being experienced by all participants. Before contacting support, please check the discussion forum for information on your problem. If you can’t find it, you can post your problem in the forum so a fellow participant or a Kaggle team member can provide help. The forums are full of useful information on the data, metric, and different approaches. We encourage you to use the forums often. If you share your knowledge, you'll find that others will share a lot in turn!\n\nIf your problem persists or it seems to be effective all participants then please [contact us](https://www.kaggle.com/contact).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}