Training my own GAN Model

latent interpolation video

I first scraped 3838 images from Flicker using the keyword “coffee”. Then, I uploaded the dataset to Runway. I used StyleGAN2 with Flickr Faces pre-trained model and 3000 steps to train my coffee model. After 5 hours, my model produced a FID 92.01. I suspect the high value is due to limited number of steps and the complexity of the dataset. Some of the coffee images had people while others did not. Some images consisted of brewed coffee while other were of coffee beans.

Screenshot of Runway

Here are some of my favorite synthesized images:

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s