![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1107630%2Ff665d901d8e42831f30c78c1be11c424%2FGAN_structure.png?generation=1562234999863233&alt=media\")
The general structure of a GAN is shown in the diagram above, using MNIST images as data. The latent sample is a random vector the generator uses to contruct it's fake images. As the generator learns through training, it figures out how to map these random vectors to recognizable images that can foold the discriminator.\nThe output of the discriminator is a sigmoid function, where 0 indicates a fake image and 1 indicates an real image. If you're interested only in generating new images, you can throw out the discriminator after training.
", "messages": [ { "id": "568030", "postDate": "07/04/2019 10:11:03", "content": "
The general structure of a GAN is shown in the diagram above, using MNIST images as data. The latent sample is a random vector the generator uses to contruct it's fake images. As the generator learns through training, it figures out how to map these random vectors to recognizable images that can foold the discriminator.\nThe output of the discriminator is a sigmoid function, where 0 indicates a fake image and 1 indicates an real image. If you're interested only in generating new images, you can throw out the discriminator after training.
", "rawMarkdown": "\n\nThe general structure of a GAN is shown in the diagram above, using MNIST images as data. The latent sample is a random vector the generator uses to contruct it's fake images. As the generator learns through training, it figures out how to map these random vectors to recognizable images that can foold the discriminator.\nThe output of the discriminator is a sigmoid function, where 0 indicates a fake image and 1 indicates an real image. If you're interested only in generating new images, you can throw out the discriminator after training.", "votes": null }, { "id": "570565", "postDate": "07/08/2019 13:18:24", "content": "Refer to the kernel: https://www.kaggle.com/grapestone5321/gan-basic-using-mnist
", "rawMarkdown": "Refer to the kernel: https://www.kaggle.com/grapestone5321/gan-basic-using-mnist", "votes": null }, { "id": "572023", "postDate": "07/10/2019 11:04:21", "content": "Also refer to the DCGAN Basic kernel: https://www.kaggle.com/grapestone5321/dcgan-basic-using-svhn
", "rawMarkdown": "Also refer to the DCGAN Basic kernel: https://www.kaggle.com/grapestone5321/dcgan-basic-using-svhn", "votes": null } ], "comments": [ { "id": 570565, "author_name": "grapestone5321", "author_url": "", "post_date": "07/08/2019 13:18:24", "content": "Refer to the kernel: https://www.kaggle.com/grapestone5321/gan-basic-using-mnist
", "votes": null, "replies": [] }, { "id": 572023, "author_name": "grapestone5321", "author_url": "", "post_date": "07/10/2019 11:04:21", "content": "Also refer to the DCGAN Basic kernel: https://www.kaggle.com/grapestone5321/dcgan-basic-using-svhn
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "568030": "\n\nThe general structure of a GAN is shown in the diagram above, using MNIST images as data. The latent sample is a random vector the generator uses to contruct it's fake images. As the generator learns through training, it figures out how to map these random vectors to recognizable images that can foold the discriminator.\nThe output of the discriminator is a sigmoid function, where 0 indicates a fake image and 1 indicates an real image. If you're interested only in generating new images, you can throw out the discriminator after training.", "570565": "Refer to the kernel: https://www.kaggle.com/grapestone5321/gan-basic-using-mnist", "572023": "Also refer to the DCGAN Basic kernel: https://www.kaggle.com/grapestone5321/dcgan-basic-using-svhn" }, "source": "meta" }