You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Are there pretrained weights for the modelnet40 alignment? The provided link has modelnet40 classification. When I try to use the same weight for alignment, the checkpoint's weight dimensions do not match.
size mismatch for backbone.0.blocks.0.inter_conv.conv.basic_conv.W: copying a param with shape torch.Size([64, 24]) from checkpoint, the shape in current model is torch.Size([32, 24]).
size mismatch for backbone.0.blocks.0.intra_conv.conv.basic_conv.W: copying a param with shape torch.Size([64, 768]) from checkpoint, the shape in current model is torch.Size([32, 384]).
size mismatch for backbone.0.blocks.0.skip_conv.weight: copying a param with shape torch.Size([64, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1, 1, 1]).
size mismatch for backbone.0.blocks.0.skip_conv.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for backbone.0.blocks.1.inter_conv.conv.basic_conv.W: copying a param with shape torch.Size([64, 1536]) from checkpoint, the shape in current model is torch.Size([32, 768]).
size mismatch for backbone.0.blocks.1.intra_conv.conv.basic_conv.W: copying a param with shape torch.Size([64, 768]) from checkpoint, the shape in current model is torch.Size([32, 384]).
.......
The text was updated successfully, but these errors were encountered:
Are there pretrained weights for the modelnet40 alignment? The provided link has modelnet40 classification. When I try to use the same weight for alignment, the checkpoint's weight dimensions do not match.
The text was updated successfully, but these errors were encountered: