search

azadis / MC-GAN

Multi-Content GAN for Few-Shot Font Style Transfer at CVPR 2018
http://bair.berkeley.edu/blog/2018/03/13/mcgan/
Other
445 stars 125 forks source link

How the dataset is generated #4

Closed SeaOfOcean closed 5 years ago

SeaOfOcean commented 5 years ago

Hi, I want to train the network on my own dataset, I'd like to know how the dataset is generated. Can you share some data preparation scripts?

azadis commented 5 years ago

preparing each dataset is different. Please take a look at our dataset here https://people.eecs.berkeley.edu/~sazadi/MCGAN/datasets. It helps you figure out the format.

SeaOfOcean commented 5 years ago

I see, thanks