Training a GAN
Thanks for trying out hypergan. This tutorial will walk you through creating your first model, exploring it, and building/deploying the generator.
Acquiring a dataset
You can acquire a dataset by having a folder full of loose images.
Getting started
First install hypergan.
Testing install
To test hypergan is installed correctly, run hypergan new . -l
You can view video card usage with nvidia-smi
Training hypergan
You can run:
hypergan train /path/to/data -c myconfig -s 256x256x3 -format png --sampler static_batch --sample_every 10
Once hypergan is working, you can sample your
Sampling your model
You've created an infinite manifold. Great! With any luck it's diverse. You can see how diverse your model is by using:
hypergan sample /path/to/data -c myconfig -s 256x256x3 -format png --sampler batch_walk
Building your model
hypergan build /path/to/data -c myconfig -s 256x256x3 -format png --sampler batch --sample_every 10
Deploying your model
You've made a great model you'd like to share. Awesome! You can deploy it to users through a few methods.
TODO
Last updated
Was this helpful?