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.
You can acquire a dataset by having a folder full of loose images.
First install hypergan.
To test hypergan is installed correctly, run
hypergan new . -l
You can view video card usage with
nvidia-smi
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
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
hypergan build /path/to/data -c myconfig -s 256x256x3 -format png --sampler batch --sample_every 10
You've made a great model you'd like to share. Awesome! You can deploy it to users through a few methods.
Last modified 2yr ago