Skip to content

Pretrain Models issues. #1

@Xuguowei-hub

Description

@Xuguowei-hub

Thank you very much for your contribution to the community.

  1. There seems to be a possible discrepancy between the correct file name on the command line and the actual file name. I found that the actual weight file in the link is called clip_best.pth, while the one I need in the command line is clip_best_fid.pth.
    python eval_t2m.py --resume-pth pretrained/net_best_fid.pth --clip_path pretrained/clip_best_fid.pth

2.I'm getting a KeyError, the checkpoint file net_best_fid.pth doesn't seem to contain the key ['net'] that the code is expecting.
print('loading checkpoint from {}'.format(args.resume_pth)) ckpt = torch.load(args.resume_pth, map_location='cpu') net.load_state_dict(ckpt['net'], strict=True) net.eval() net.cuda()
Therefore, it raises a KeyError.
1714980684012

Looking forward to your reply!

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