Pretrained weights for modelnet alignment

[zeroAska]

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]).
.......