This directory contains all jobs used for training or fine-tuning various models.
The stylegan2-ada folder contains:
def-styleGan2AdaPytorchDataSetupBatch.shis the SBatch script for preparing the training dataset for StyleGAN2-ADA. The script uses thedef-whkchuncluster.def-styleGAN2AdaPytorchTrainBatch.shis the SBatch script for training. The script uses thedef-whkchuncluster.ctb-styleGAN2AdaPytorchGenerateBatch.shis the SBatch script for generating an image from the StyleGAN2-ADA model. The script uses thectb-whkchuncluster.def-styleGAN2AdaPytorchGenerateBatch.shis the SBatch script that also can be used to generate images from the StyleGAN2-ADA model. This version uses thedef-whkchuncluster.requirements.txtshows the packages used by the PyTorch implementation of StyleGAN2-ADA. Note that this is not used to create the environment, but to document the environment after it was created.
See the StyleGAN2-ADATraining.md in the documentation folder for details on how to set up the environment.
The stylegan3 directory contains:
requirements.txtis used with other module installations to set up the environment for training the stylegan3 model with the Bliss single characters.job_stylegan3.shis the job script submitted in the Cedar platform to perform the training.
See the TrainStyleGAN3Model.md in the documentation folder for details on how to about how to train this model, training results and the conclusion about how useful it is.