agents: The main training files (architecture, optimisation scheme) are inagents.trainingModuleis an abstract agent that regroup some basic training functions (similar to Pytorch lighting abstraction. Most of the optimization/training procedure is isfaderNet(the most simple one), the others build on it by just changing a few key functions (group the inputs, define the nets):faderNet: architecture of G1 without the normals, contains most of the code (equivalent to faderNet)faderNet_with_normals: G1faderNet_with_normals_2steps: G2faderNet_with_normals_illum: a test of G1 + illumination map
configs: configuration files to launch the trainings or testdatasets: code to read the datasetsexperiments: snapshots of experimentsmodels: code of the networksutils: various utilities
forked from bluestyle97/STGAN-pytorch
jdelanoy/STGAN-pytorch
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Resources
Stars
Watchers
Forks
Packages 0
No packages published
Languages
- Python 100.0%