GANã®ç™ºå±•ã®æ´å²ã‚’振り返るï¼GANã®åŒ…括的ãªã‚µãƒ¼ãƒ™ã‚¤è«–æ–‡ã®ç´¹ä»‹(アルゴリズム編)3ã¤ã®è¦ç‚¹ ✔ï¸æ§˜ã€…ãªåˆ†é‡Žã§ä½¿ç”¨ã•ã‚Œã¦ã„ã‚‹ 「GANã€ã®åŒ…括的ãªã‚µãƒ¼ãƒ™ã‚¤è«–æ–‡ã®ç´¹ä»‹ ✔ï¸ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ç·¨ã§ã¯ã€ã€ŒGANã€ã®ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ã«ç„¦ç‚¹ã‚’絞ã£ã¦æ§˜ã€…ãªã‚¢ãƒ—ãƒãƒ¼ãƒã‚’紹介 âœ”ï¸ ã“ã®è¨˜äº‹ã§ã€ŒGANã€ã®æœ€æ–°å‹•å‘ã¾ã§ã‚’ã‚ャッãƒã‚¢ãƒƒãƒ—å¯èƒ½ A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications written by Jie Gui, Zhenan Sun, Yonggang Wen, Dacheng Tao, Jieping Ye (Submitted on 20 Jan 2020) subjects : Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) ã¯ã˜ã‚ã« 2014å¹´ã«ç”»åƒç”Ÿæˆã®ãŸã‚ã®ã‚¢
訓練ã—ã¦ã„ãªã„クラスã®ç”»åƒã‚’生æˆå¯èƒ½ï¼ï¼Ÿãƒ¡ãƒˆãƒªãƒƒã‚¯ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ã‚’å°Žå…¥ã—ãŸOpenGAN
GANã®ç™ºå±•ã®æ´å²ã‚’振り返るï¼GANã®åŒ…括的ãªã‚µãƒ¼ãƒ™ã‚¤è«–æ–‡ã®ç´¹ä»‹(応用編)
GANã®é€²åŒ–å½¢ç¾ã‚‹! 幾何å¦ã‚’利用ã—ãŸæ–°ãŸãªãƒ¢ãƒ‡ãƒ«ã€ŒSphere GANã€ç†è«–
低解åƒåº¦ãƒ“デオもã™ãã«é«˜è§£åƒåº¦ã«å¤‰æ›ã§ãる超解åƒã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ TecoGANãŒã™ã”ã„
[最新論文/GAN] ラベルãŒãªã„ãªã‚‰æŽ¨æ¸¬ã™ã‚Œã°ã„ã„。 - Qiita![[最新論文/GAN] ラベルãŒãªã„ãªã‚‰æŽ¨æ¸¬ã™ã‚Œã°ã„ã„。 - Qiita](https://cdn-ak-scissors.b.st-hatena.com/image/square/89792d24bfcbaed2f7f5f8a9a554f92748054a07/height=288;version=1;width=512/https%3A%2F%2Fqiita-user-contents.imgix.net%2Fhttps%253A%252F%252Fcdn.qiita.com%252Fassets%252Fpublic%252Farticle-ogp-background-412672c5f0600ab9a64263b751f1bc81.png%3Fixlib%3Drb-4.0.0%26w%3D1200%26mark64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZ3PTk3MiZoPTM3OCZ0eHQ9JTVCJUU2JTlDJTgwJUU2JTk2JUIwJUU4JUFCJTk2JUU2JTk2JTg3JTJGR0FOJTVEJTIwJUUzJTgzJUE5JUUzJTgzJTk5JUUzJTgzJUFCJUUzJTgxJThDJUUzJTgxJUFBJUUzJTgxJTg0JUUzJTgxJUFBJUUzJTgyJTg5JUU2JThFJUE4JUU2JUI4JUFDJUUzJTgxJTk5JUUzJTgyJThDJUUzJTgxJUIwJUUzJTgxJTg0JUUzJTgxJTg0JUUzJTgwJTgyJnR4dC1hbGlnbj1sZWZ0JTJDdG9wJnR4dC1jb2xvcj0lMjMxRTIxMjEmdHh0LWZvbnQ9SGlyYWdpbm8lMjBTYW5zJTIwVzYmdHh0LXNpemU9NTYmcz00N2ZkZDNiNmQ5YjA0OGRkMGE4YjdmOWRiMmQ4NTFkNQ%26mark-x%3D142%26mark-y%3D57%26blend64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZoPTc2Jnc9NzcwJnR4dD0lNDBQaG9lYm9vb28mdHh0LWNvbG9yPSUyMzFFMjEyMSZ0eHQtZm9udD1IaXJhZ2lubyUyMFNhbnMlMjBXNiZ0eHQtc2l6ZT0zNiZ0eHQtYWxpZ249bGVmdCUyQ3RvcCZzPWY5MTEwNzA0OWVjNTk4ZWYyY2FkMTY5MzI1NzgzNzY5%26blend-x%3D142%26blend-y%3D486%26blend-mode%3Dnormal%26s%3D911774cdadc5ddf53bf781acc1d8e6fd)
GANã«ã‚ˆã‚‹è¶…解åƒãŒã‚‚ãŸã‚‰ã™æ–°ã—ã„æ–¹å‘性ã¨ã€ŒThe Perception-Distortion Tradeoffã€ã®è©± - Think more, try less
Goodfellowã•ã‚“ã®GANã®ã‚ªã‚¹ã‚¹ãƒ¡è«–æ–‡10é¸ã¾ã¨ã‚ (2018/02) - ディープラーニングæ±äº¬
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
https://elix-tech.github.io/ja/2017/02/07/gan.html
GitHub - kaonashi-tyc/zi2zi: Learning Chinese Character style with conditional GAN
DCGANã§å刺ã®ãƒ‡ã‚¶ã‚¤ãƒ³ã‚’試ã¿ãŸ - Stimulator
ã¯ã˜ã‚ã¦ã®GAN
StackGANã«ã‚ˆã‚‹ãƒ•ã‚©ãƒ³ãƒˆã®éŒ¬é‡‘è¡“ - ã«ã»ã‚“ã”ã®ã‚Œã‚“ã—ã‚…ã†
å–り急ãŽpix2pixã§éŠã‚“ã§ã¿ãŸ(追記ã‚ã‚Š) - Qiita
Engadget | Technology News & Reviews
DCGAN - How does it work?
IIBMP2016 深層生æˆãƒ¢ãƒ‡ãƒ«ã«ã‚ˆã‚‹è¡¨ç¾å¦ç¿’
{{#tags}}- {{label}}
{{/tags}}