GitHub / Gregoritsch3 / DL_NeuralStyleTransfer
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.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gregoritsch3%2FDL_NeuralStyleTransfer
PURL: pkg:github/Gregoritsch3/DL_NeuralStyleTransfer
Stars: 0
Forks: 0
Open issues: 0
License: None
Language: Jupyter Notebook
Size: 7.31 MB
Dependencies parsed at: Pending
Created at: 3 months ago
Updated at: 2 months ago
Pushed at: 2 months ago
Last synced at: 2 months ago
Topics: computer-vision, deep-learning, instance-normalization, neural-style-transfer, tensorflow