ma-xu / Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

can't load detection pretrained model

Missyfirst opened this issue · comments

excuse me,there is a error of detection pretrained model, raise error:
size mismatch for backbone.network.0.0.mlp.fc1.weight: copying a param with shape torch.Size([512, 64, 1, 1]) from checkpoint, the
shape in current model is torch.Size([512, 64]).
size mismatch for backbone.network.0.0.mlp.fc2.weight: copying a param with shape torch.Size([64, 512, 1, 1]) from checkpoint, the
shape in current model is torch.Size([64, 512]).
Hope you can provide new checkpoints. thank you.

I am also having the same issue. Have you solved it?

try followings:

  1. fix MLP in context_cluster.py
    image

  2. fix Cluster in context_cluster.py
    image