Skip to content

關於kernel size  #79

@ntut110368136

Description

@ntut110368136

如果我想要更改CNN模型的kernel size,例如改成5*5大小,以便看是否有更高的PSNR。
我跟改了model_x 檔案第52行"layers = [nn.Conv2d(in_filters, out_filters, 5, stride=2, padding=1)]"
跑出了錯誤訊息 "RuntimeError: Calculated padded input size per channel: (7 x 7). Kernel size: (8 x 8). Kernel size can't be greater than actual input size" ,想請問作者如何解決。

謝謝您。

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions