The following analogy is very nice:\n```\nLet’s say there is this very cool party going on at your neighborhood that you really want to go. But, there is a problem. To get into the party you need a special ticket that was long sold out.
\n\nSince expectations are very high, the party’s organization hired a qualified security agency. Their primary goal is to not allow anyone to crash the party. To do that, they placed a lot of guards at the party’s entrance to check everyone’s tickets for authenticity. Since you don’t have any martial artistic gifts, the only way to get through is by fooling them with a fake ticket.
\n\nThere is a big problem with this plan though, you never actually saw how the ticket looks like. Even if you design a ticket based on your creativity, it’s almost impossible to fool the guards at your first trial. Besides, you can’t show off your face until you have a very decent replica of the party’s pass.
\n\nTo help with your problems, you decide to call your friend Bob to do the dirty job for you.
\n\nBob’s mission is very simple, he will try to get into the party with your fake pass. If he gets denied, he will come back to you with useful advices on how the ticket should look like. Based on that feedback, you make a new version of the ticket and hands it to Bob who goes to try again. This process keeps repeating until you become able to design a perfect replica.\n```\n2. https://towardsdatascience.com/semi-supervised-learning-with-gans-9f3cb128c5e\nThis shows how to use GAN in semi-supervised learning.
\n\nhttps://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f\nA list of GAN tutorial with code in tensorflow/pytorch
https://sites.google.com/view/cvpr2018tutorialongans/\nCVPR 2018 Tutorial on GANs
https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-a-cifar-10-small-object-photographs-from-scratch/?fbclid=IwAR1HCR4BAvFna8QWPx4emuyZeHVdF5iAooVOAct_KxBSSnXs7duvQHAznMk\nJason Brownlee's intro on using GAN for customized dataset
https://github.com/ozanciga/gans-with-pytorch\nReferenced from Vladislav Bakhteev's kernel (@speedwagon) - Various implementations of GANs using Pytorch
The following analogy is very nice:\n```\nLet’s say there is this very cool party going on at your neighborhood that you really want to go. But, there is a problem. To get into the party you need a special ticket that was long sold out.
\n\nSince expectations are very high, the party’s organization hired a qualified security agency. Their primary goal is to not allow anyone to crash the party. To do that, they placed a lot of guards at the party’s entrance to check everyone’s tickets for authenticity. Since you don’t have any martial artistic gifts, the only way to get through is by fooling them with a fake ticket.
\n\nThere is a big problem with this plan though, you never actually saw how the ticket looks like. Even if you design a ticket based on your creativity, it’s almost impossible to fool the guards at your first trial. Besides, you can’t show off your face until you have a very decent replica of the party’s pass.
\n\nTo help with your problems, you decide to call your friend Bob to do the dirty job for you.
\n\nBob’s mission is very simple, he will try to get into the party with your fake pass. If he gets denied, he will come back to you with useful advices on how the ticket should look like. Based on that feedback, you make a new version of the ticket and hands it to Bob who goes to try again. This process keeps repeating until you become able to design a perfect replica.\n```\n2. https://towardsdatascience.com/semi-supervised-learning-with-gans-9f3cb128c5e\nThis shows how to use GAN in semi-supervised learning.
\n\nhttps://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f\nA list of GAN tutorial with code in tensorflow/pytorch
https://sites.google.com/view/cvpr2018tutorialongans/\nCVPR 2018 Tutorial on GANs
https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-a-cifar-10-small-object-photographs-from-scratch/?fbclid=IwAR1HCR4BAvFna8QWPx4emuyZeHVdF5iAooVOAct_KxBSSnXs7duvQHAznMk\nJason Brownlee's intro on using GAN for customized dataset
https://github.com/ozanciga/gans-with-pytorch\nReferenced from Vladislav Bakhteev's kernel (@speedwagon) - Various implementations of GANs using Pytorch
thank you for sharing.\nI 'll check it.
", "rawMarkdown": "thank you for sharing.\nI 'll check it.", "votes": null }, { "id": "565889", "postDate": "07/01/2019 13:57:03", "content": "I have also written a post. Have a look: https://medium.com/@shwetagoyal41/gans-a-brief-introduction-to-generative-adversarial-networks-f06216c7200e
", "rawMarkdown": "I have also written a post. Have a look: https://medium.com/@shwetagoyal41/gans-a-brief-introduction-to-generative-adversarial-networks-f06216c7200e", "votes": null } ], "comments": [ { "id": 565454, "author_name": "kageyama", "author_url": "", "post_date": "07/01/2019 01:09:19", "content": "thank you for sharing.\nI 'll check it.
", "votes": null, "replies": [] }, { "id": 565889, "author_name": "shwetagoyal4", "author_url": "", "post_date": "07/01/2019 13:57:03", "content": "I have also written a post. Have a look: https://medium.com/@shwetagoyal41/gans-a-brief-introduction-to-generative-adversarial-networks-f06216c7200e
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "565319": "1. https://www.freecodecamp.org/news/an-intuitive-introduction-to-generative-adversarial-networks-gans-7a2264a81394/\n\nThe following analogy is very nice:\n```\nLet’s say there is this very cool party going on at your neighborhood that you really want to go. But, there is a problem. To get into the party you need a special ticket that was long sold out.\n\nSince expectations are very high, the party’s organization hired a qualified security agency. Their primary goal is to not allow anyone to crash the party. To do that, they placed a lot of guards at the party’s entrance to check everyone’s tickets for authenticity. Since you don’t have any martial artistic gifts, the only way to get through is by fooling them with a fake ticket.\n\nThere is a big problem with this plan though, you never actually saw how the ticket looks like. Even if you design a ticket based on your creativity, it’s almost impossible to fool the guards at your first trial. Besides, you can’t show off your face until you have a very decent replica of the party’s pass. \n\nTo help with your problems, you decide to call your friend Bob to do the dirty job for you.\n\nBob’s mission is very simple, he will try to get into the party with your fake pass. If he gets denied, he will come back to you with useful advices on how the ticket should look like. Based on that feedback, you make a new version of the ticket and hands it to Bob who goes to try again. This process keeps repeating until you become able to design a perfect replica.\n```\n2. https://towardsdatascience.com/semi-supervised-learning-with-gans-9f3cb128c5e\nThis shows how to use GAN in semi-supervised learning.\n\n3. https://medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f\nA list of GAN tutorial with code in tensorflow/pytorch\n\n4. https://sites.google.com/view/cvpr2018tutorialongans/\nCVPR 2018 Tutorial on GANs\n\n5. https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-a-cifar-10-small-object-photographs-from-scratch/?fbclid=IwAR1HCR4BAvFna8QWPx4emuyZeHVdF5iAooVOAct_KxBSSnXs7duvQHAznMk\nJason Brownlee's intro on using GAN for customized dataset\n\n6. https://github.com/ozanciga/gans-with-pytorch\nReferenced from Vladislav Bakhteev's kernel (@speedwagon) - Various implementations of GANs using Pytorch", "565454": "thank you for sharing.\nI 'll check it.", "565889": "I have also written a post. Have a look: https://medium.com/@shwetagoyal41/gans-a-brief-introduction-to-generative-adversarial-networks-f06216c7200e" }, "source": "meta" }