Open yeong95 opened 2 years ago
The stylegan generator of genforce is refactored. The whole training pipeline can be found here, this pytorch repo only supports inference.
Thank you for reply.
And one more question: Is the inversion process in genforce repo the same as the inversion process in this repo?
No, the genforce supports training the encoder in this repo.
I trained stylegan generator from genforce (https://github.com/genforce/genforce/tree/2ad04974cfaeba20b93c806531f987f06cc5c328)
But when loading weights from trained model the keys doesn't match each other.
How do i fix this?