Tag：Discriminator
-
Plug and play! Rising point artifact in video super score: iseebeter
Compile | CVReport | I love computer vision (wechat ID: aicvml) CNN makes the super score results more real, and Gan makes the super score results Fuller, so CNN + Gan = good! Adding a discriminator component can increase the result by 0.32db, plug and play, rising point artifact! Whether it is also feasible in […]
-
Fake news is everywhere: I created an open source project to mark fake news through deep learning
The rise of fake news has forced everyone with a social media account to become a detective, responsible for determining whether a post is genuine before it is published. However, false news will still cross our defense line and spread rapidly on the network, which is aggravated by the ignorance and carelessness of users. As […]
-
Rollover scene: I used pytorch and Gan to make a failure model to generate Magic Baby
Preface Magic baby is already a household animation. Let’s confirm whether we can use deep learning to automatically create a new Pokemon for him.I finally managed to generate a Pokemon like image using the generation countermeasure network (GAN), but this image doesn’t look like a magic baby.Although this attempt failed, I think other people may […]
-
Google released the AI language model Electra as an open source model on tensorflow
In a recent study, Google researchers proposed “effective learning of an encoder that accurately classifies token substitutions” (Electra), an AI language training technology that outperforms existing methods with the same amount of computing resources. A few months after the release, the co authors released tensorflow’s code base (and pre trained models), laying the foundation for […]