Skip to content

question for pretrained net #249

Open

Description

@lfytmly

in model = eval , it shows RuntimeError: Weights named 'conv2d_1/filters:0' not found in network. Hint: set argument skip=Ture if you want to skip redundant or mismatch weights.

i download g.npz and d.npz and pretrained vgg19 in your readme

Activity

  1. ZIYUANLI-star commented on May 3, 2023

    @ZIYUANLI-star

    meet too

  2. YQL-Skorpion commented on Jun 23, 2023

    @YQL-Skorpion

    Same, using pytorch 1.10.1 as specified. default athe default argument of

    Edit: problem solved by following the hint, changing line 186 skip=False to skip=True in (env)\lib\site-packages\tensorlayerx\nn\core\core_torch.py.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions