Skip to content
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

stylegan_v2_256是否可以训练生成512或者1024尺寸的图片,如何配置yaml? #837

Open
zhw511006 opened this issue Mar 1, 2024 · 2 comments
Assignees

Comments

@zhw511006
Copy link

在config文件夹里面找到了stylegan_v2_256_ffhq.yaml配置,
model:
name: StyleGAN2Model
generator:
name: StyleGANv2Generator
size: 256
style_dim: 512
n_mlp: 8
discriminator:
name: StyleGANv2Discriminator
size: 256

这样训练完的模型可以生成尺寸为256的图片,简单修改其中size为512或者1024,进行训练的时候直接报错,如下:

ValueError: (InvalidArgument) Input(Y) has error dim.Y'dims[0] must be equal to 12800But received Y'dims[0] is 8192
[Hint: Expected y_dims[y_ndim - 2] == K, but received y_dims[y_ndim - 2]:8192 != K:12800.] (at /paddle/paddle/phi/kernels/impl/matmul_kernel_impl.h:315)
[operator < matmul_v2 > error]

请问如何修改yaml配置可以生成512或者1024尺寸的图片,谢谢!

@jerrywgz
Copy link
Collaborator

jerrywgz commented Mar 4, 2024

在组网阶段一些输入shape也需要检查下

@1196228233
Copy link

有没有一种可能把大图切成多个256小图,生成后再拼接回去。就是不知道会不会有接痕?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants