18 Impressive Applications of Generative Adversarial Networks (GANs) - MachineLearningMastery.com
A Generative Adversarial Network, or GAN, is a type of neural network architecture for generative modeling. Generative modeling involves using a model to generate new examples that plausibly come from an existing distribution of samples, such as generating new photographs that are similar but specifically different from a dataset of existing photographs. A GAN is a generative model that is trained
conditional DRAGANã§ã®ãƒ©ãƒ™ãƒ«ã®ä¸Žãˆæ–¹ - 緑茶æ€è€ƒãƒ–ãƒã‚°
conditional GANã®ãƒ©ãƒ™ãƒ«ã®ä¸Žãˆæ–¹ã¯è‰²ã€…ã‚り〠毎回ã©ã†ã™ã‚Œã°è‰¯ã„ã‹ã‚ˆãã‚ã‹ã‚‰ãšè¿·ã£ã¦ã—ã¾ã†ã€‚ githubã®å®Ÿè£…ã‚’ã¿ã‚‹ã¨æ§˜ã€…ã«æ›¸ã‹ã‚Œã¦ã„る。 文献をèªã‚€ã‚ˆã‚Šã‚‚色んãªäººã®å®Ÿè£…ã‚’æ¼ã‚‹ã»ã†ãŒçŸ¥è¦‹ãŒè²¯ã¾ã‚‹ã“ã®é ƒã€‚ 今回ã¯MNISTã«å¯¾ã—ã¦DRAGANを用ã„ã¦ã€ ãã®ä¸ã§ã‚‚よã見ã‹ã‘ã‚‹è¨å®šã‚’評価ã—ã¦ã¿ã‚‹ã€‚ （DRAGANを用ã„ãŸã®ã¯å˜ã«å®‰å®šã—ã¦ã„ã‚‹ã¨ã„ã†ç†ç”±ã®ã¿ï¼‰ 以下ã®è¨å®šã®ã‚‚ã¨ã§ã„ãšã‚Œã®è©•ä¾¡ã‚‚è¡Œã£ãŸï¼Ž batchsizeã¯64 optimizerã¯Adamを使用（learning rate:1e-4） Generatorã®æ§‹é€ ã¯3層(1:FC層, 2:Deconv層, 3:Deconv層)， 出力層ã®æ´»æ€§åŒ–関数ã¯tanhã§ã¯ãªãsigmoidを使用 Discriminatorã®æ§‹é€ ã¯3層(1:Conv層, 2:Conv層, 3: FC層) BatchNormalizationä¸ä½¿ç”¨
1
ランã‚ング
ランã‚ング
ランã‚ング
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
処ç†ã‚’実行ä¸ã§ã™
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
{{#tags}}- {{label}}
{{/tags}}