A DL project that implements Neural Style Transfer on images using a pretrained model, a VGG19-based architecture, and a Feed-Forward architecture after Johnson et al. (2016). The different models utilize custom TensorFlow training loops, cost functions and layers (InstanceNormalization). Various tendencies of such architectures are discussed. The results are satisfying, yet further improvements are always possible.
-
Notifications
You must be signed in to change notification settings - Fork 0
A DL project that implements Neural Style Transfer on images using a pretrained model, a VGG19-based architecture, and a Feed-Forward architecture after Johnson et al. (2016). The different models utilize custom TensorFlow training loops, cost functions and layers (InstanceNormalization). Various tendencies of such architectures are discussed.
Gregoritsch3/DL_NeuralStyleTransfer
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A DL project that implements Neural Style Transfer on images using a pretrained model, a VGG19-based architecture, and a Feed-Forward architecture after Johnson et al. (2016). The different models utilize custom TensorFlow training loops, cost functions and layers (InstanceNormalization). Various tendencies of such architectures are discussed.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published