We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
我请问在训练512x512的时候,是再下采样一次,使用16x16的latent size, 还是把v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16)扩展为v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16....32), 还是直接使用v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16),最后卷积到latent size=32就好?
The text was updated successfully, but these errors were encountered:
@YilanWang 是 (1,2,...32),可参考 https://github.com/FoundationVision/VAR/blob/main/utils/arg_util.py#L246
Sorry, something went wrong.
多谢作者~看到了,我发现复现的时候channel如果比较少(也就是网络小一点),multiscale vq很难收敛啊,不知道是不是复现有什么bug,希望作者大大早日开源VAE的复现
No branches or pull requests
我请问在训练512x512的时候,是再下采样一次,使用16x16的latent size, 还是把v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16)扩展为v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16....32), 还是直接使用v_patch_nums=(1, 2, 3, 4, 5, 6, 8, 10, 13, 16),最后卷积到latent size=32就好?
The text was updated successfully, but these errors were encountered: