-
Notifications
You must be signed in to change notification settings - Fork 7
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to Inference? #17
Comments
content_font is the same directory you create in training phase. img_path is a directory containing bunch of reference images of a font. |
What do you mean by reference images of a font? Words of fonts in train_font in build_trainset.sh? |
img_path is the test font images. gen_unis contains the characters u about to infer. it should not be empty... |
What does ref_unis refer to? It contains original_meta[target_name]. Are both ref_unis and gen_unis the same? |
What should be put for arguments --content_font and --img_path?
Is this content_font the same directory as the content_font in build_datasets/build_trainset.sh? Should the directory contains the training content words images?
What should be contained in img_path? Am I correct to put some words apart from those in content_font directory with the same font with the images in content_font?
The "charlist" of the content font is empty and also "gen_unis" is empty when I run the inference.sh. Please help.
The text was updated successfully, but these errors were encountered: