animate-me icon indicating copy to clipboard operation
animate-me copied to clipboard

Published 20 hours ago • verified publisher icon Aneureka

Sharing training process

Open FantasyJXF opened this issue 5 years ago • 2 comments

I use the selfie2anime datasets the Author provided, and replace like one thousand images that was not so good based on aesthetics.

It's so time consuming to train the model.

I use Tesla P40 and resize the image size to 128x128, it took me 7days to train the model.

OMG, the result is no better than the original.

FantasyJXF avatar Sep 12 '19 03:09 FantasyJXF

Have you trained the model based on the pretrained one the author provided? I have tried to train it on my datasets (around 5000 pictures) also but it's very very life wasting...

Aneureka avatar Sep 12 '19 03:09 Aneureka

Also tried to train base on the pretrained 100epoch model, the result was not so good. So I retrained the model with PYTORCH release.

And I don't know what to do to improve the model performance, the present model has too many badcase.

What's your opinion?

FantasyJXF avatar Sep 12 '19 03:09 FantasyJXF